Downloads · 30 days
0
siddharthmb/2026.TA.features_2026.TA.gemma2_2b_sparse_probe_l1_0p016_tc8192_decb_l1w0.016_tarb_h8cde056f3e36
2026.TA.features_2026.TA.gemma2_2b_sparse_probe_l1_0p016_tc8192_decb_l1w0.016_tarb_h8cde056f3e36 is a machine learning model from siddharthmb. 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 circuit-tracer.
Packed circuit-tracer feature cache produced by analysis.features.collect.
Downloads · 30 days
0
Access
Public
Updated Oct 11, 2026
Repo size
2.7 GB
Likes
0
Public
Click a slice to open those files.
.bin2.4 GB · 88%
From the Hugging Face model README
Packed circuit-tracer feature cache produced by analysis.features.collect.
Complete.
Attribution graphs read this repo as a feature scan: pass --feature_data_path siddharthmb/2026.TA.features_2026.TA.gemma2_2b_sparse_probe_l1_0p016_tc8192_decb_l1w0.016_tarb_h8cde056f3e36 (adapter features) or --base_feature_data_path siddharthmb/2026.TA.features_2026.TA.gemma2_2b_sparse_probe_l1_0p016_tc8192_decb_l1w0.016_tarb_h8cde056f3e36 (GemmaScope base features) to python -m analysis.attribution.graphs.build_graphs; the viewer started by python -m analysis.attribution.serve then streams a clicked node's examples from features/index.json.gz and features/layer_N.bin in this repo.
Read one feature by its cantor id without the viewer:
from analysis.features.collect.hub import load_circuit_tracer_feature_from_hub
from helpers.ids import cantor_pair
feature = load_circuit_tracer_feature_from_hub("siddharthmb/2026.TA.features_2026.TA.gemma2_2b_sparse_probe_l1_0p016_tc8192_decb_l1w0.016_tarb_h8cde056f3e36", cantor_pair(layer, idx))
Browse the whole collection with the dashboard, which reads a collection dir on the cluster (feature_metadata.json, the packed store circuit_tracer_features/, the histogram and annotation sidecars):
uv run python -m analysis.features.dashboard --data_dir <the collection's output dir on the cluster>
{'fineweb': 62706474, 'chat': 46982745}