Downloads · 30 days
0
ai-safety-institute/apollo-google-gemma-3-12b-it
apollo-google-gemma-3-12b-it is a machine learning model from ai-safety-institute. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for pytorch. The card lists the license as mit.
A probe trained to detect deceptive behaviour in google/gemma-3-12b-it using residual stream activations, following the methodology from Detecting Strategic Deception in Language Models (Apollo Research, 2024).
Downloads · 30 days
0
Access
Public
Updated Jun 10, 2026
Repo size
7.1 GB
Likes
0
Public
Click a slice to open those files.
.pt7.1 GB · 100%
From the Hugging Face model README
A probe trained to detect deceptive behaviour in google/gemma-3-12b-it using residual stream activations, following the methodology from Detecting Strategic Deception in Language Models (Apollo Research, 2024).
uv add lie-detectors # or: pip install lie-detectors
from lie_detectors import get_probe
probe = get_probe("ai-safety-institute/apollo-google-gemma-3-12b-it")
The default checkpoint is the best performer from the hyperparameter sweep (l_38_lm_500000_ar_lr.pt). To pick a specific checkpoint, pass filename=:
probe = get_probe("ai-safety-institute/apollo-google-gemma-3-12b-it", filename="l_40_ar_mlp_wd_0_001_lr_0_0001_ep_100.pt")
See UKGovernmentBEIS/lie_detectors for the loading library.
Use sweep.json to see all 296 available checkpoints and their metrics.
| Property | Value |
|---|---|
| Target model | google/gemma-3-12b-it |
| Safe name | google--gemma-3-12b-it |
| Default checkpoint | l_38_lm_500000_ar_lr.pt |
| Available checkpoints | 296 |
| Calibration | Threshold set at 1% FPR on Alpaca (honest baseline) |
Probes are trained on an instructed pairs dataset (model instructed to be deceptive vs. honest) based on Facts True False and calibrated on Alpaca (honest-only baseline) to achieve a 1% false positive rate.
@misc{goldowskydill2025detectingstrategicdeceptionusing,
title={Detecting Strategic Deception Using Linear Probes},
author={Nicholas Goldowsky-Dill and Bilal Chughtai and Stefan Heimersheim and Marius Hobbhahn},
year={2025},
eprint={2502.03407},
archivePrefix={arXiv},
primaryClass={cs.LG},
url={https://arxiv.org/abs/2502.03407},
}
@misc{cooney2026liedetectors,
title={``Did you lie?'' Evaluating Lie Detectors across Model Scale and Belief-Verified Model Organisms},
author={Alan Cooney and David Africa and Geoffrey Irving},
year={2026},
month={May},
}