Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
Solshine
/
gemma-4-e2b-scope-v1-L17-batchtopk-k64-seed17
like
1
HuggingFaceFW/fineweb-edu
English
sparse-autoencoder
mechanistic-interpretability
sae-lens
gemma-4
batch-topk
arxiv:
2412.06410
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
Copy to bucket
new
3ce5af7
gemma-4-e2b-scope-v1-L17-batchtopk-k64-seed17
906 MB
Ctrl+K
Ctrl+K
1 contributor
History:
31 commits
Solshine
Colab T4 checkpoint: 16,001,024 tokens
3ce5af7
verified
about 2 months ago
.gitattributes
Safe
1.52 kB
initial commit
about 2 months ago
README.md
Safe
491 Bytes
Checkpoint README: 14,003,200 tokens
about 2 months ago
cfg.json
Safe
266 Bytes
Colab T4 checkpoint: 2,000,896 tokens
about 2 months ago
optimizer.pt
pickle
Detected Pickle imports (3)
"torch.FloatStorage"
,
"collections.OrderedDict"
,
"torch._utils._rebuild_tensor_v2"
What is a pickle import?
604 MB
xet
Colab T4 checkpoint: 14,003,200 tokens
about 2 months ago
progress.json
Safe
211 Bytes
Colab T4 checkpoint: 14,003,200 tokens
about 2 months ago
sae_weights.pt
pickle
Detected Pickle imports (3)
"torch._utils._rebuild_tensor_v2"
,
"collections.OrderedDict"
,
"torch.FloatStorage"
What is a pickle import?
302 MB
xet
Colab T4 checkpoint: 16,001,024 tokens
about 2 months ago
