Downloads · 30 days
0
gemma4-31b-fp8block-finaltoken-sae-200m
ddasd/gemma4-31b-fp8block-finaltoken-sae-200m
gemma4-31b-fp8block-finaltoken-sae-200m is a machine learning model from ddasd. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as other.
TopK sparse autoencoder trained on vLLM tokenembed final-token embeddings from RedHatAI/gemma-4-31B-it-FP8-block.
Access
Public
Updated May 23, 2026
Repo size
2.8 GB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.safetensors2.8 GB · 100%
At a glance
- License
- other
- Access
- Public
- Created
- May 23, 2026
- Updated
- May 23, 2026
- SHA
- 51f40094
Base models
Model card
From the Hugging Face model README
Gemma 4 31B FP8 Block Final-Token SAE
TopK sparse autoencoder trained on vLLM token_embed final-token embeddings from RedHatAI/gemma-4-31B-it-FP8-block.
This is a final-token / embedding-surface SAE, not an internal residual-stream layer SAE.
Training Summary
- Base model:
RedHatAI/gemma-4-31B-it-FP8-block - Activation surface: vLLM token embedding / final-token embeddings
- Architecture: TopK SAE
- Input dimension: 5376
- Dictionary size: 65536
- TopK: 128
- Aux TopK: 2688
- Training tokens: 200,000,000
- Final EMA variance explained: approximately 0.875
- Final dead features: 2693 / 65536
Files
gemma4_31b_fp8block_finaltoken_sae_final.safetensors: final SAE weightsgemma4_31b_fp8block_finaltoken_sae_cfg.json: configuration and training metadata
The weights use keys W_enc, W_dec, b_enc, b_dec, and last_fired.
- License
- other
- Created
- May 23, 2026
- Updated
- May 23, 2026