Downloads · 30 days
8
30% of all-time downloads
gemma-hook-layer-0-step-3000
thejaminator/gemma-hook-layer-0-step-3000
gemma-hook-layer-0-step-3000 is a machine learning model from thejaminator. 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 peft.
This is a LoRA (Low-Rank Adaptation) adapter trained for SAE (Sparse Autoencoder) introspection tasks.
All-time downloads
27
Public
Repo size
903 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors864 MB · 96%
At a glance
- Library
- peft
- Model type
- gemma2
- Access
- Public
- Created
- Aug 28, 2025
- Updated
- Aug 28, 2025
- SHA
- 507389f6
Base models
Model card
From the Hugging Face model README
LoRA Adapter for SAE Introspection
This is a LoRA (Low-Rank Adaptation) adapter trained for SAE (Sparse Autoencoder) introspection tasks.
Base Model
- Base Model:
google/gemma-2-9b-it - Adapter Type: LoRA
- Task: SAE Feature Introspection
Usage
from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel
# Load base model and tokenizer
base_model = AutoModelForCausalLM.from_pretrained("google/gemma-2-9b-it")
tokenizer = AutoTokenizer.from_pretrained("google/gemma-2-9b-it")
# Load LoRA adapter
model = PeftModel.from_pretrained(base_model, "thejaminator/gemma-hook-layer-0-step-3000")
Training Details
This adapter was trained using the lightweight SAE introspection training script to help the model understand and explain SAE features through activation steering.
- Library
- peft
- Type
- gemma2
- Created
- Aug 28, 2025
- Updated
- Aug 28, 2025