Neuronpedia
Get Started
API
Releases
Jump To
Search
Models
Circuit Tracer
NEW
Steer
SAE Evals
Exports
Slack
Blog
Privacy & Terms
Contact
Sign In
© Neuronpedia 2025
Privacy & Terms
Blog
GitHub
Slack
Twitter
Contact
Home
Joseph Bloom · Initial Gemma-2B SAEs
Gemma-2B
Residual Stream
12-RES-JB
7870
Prev
Next
MODEL
12-res-jb
Source/SAE
INDEX
Go
Explanations
references to specific cultural or media elements
oai_token-act-pair · gpt-4o-mini
Triggered by @bot
No Scores
New Auto-Interp
AutoInterp Type
claude-3-5-haiku-20241022
Generate
Top Features by Cosine Similarity
Configuration
jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.12.hook_resid_post_16384
How To Load
Prompts (Dashboard)
24,576 prompts, 128 tokens each
Dataset (Dashboard)
HuggingFaceFW/fineweb
Features
16,384
Data Type
torch.float32
Hook Point
blocks.12.hook_resid_post
Architecture
standard
Context Size
1,024
Dataset
HuggingFaceFW/fineweb
Hook Point Layer
12
Activation Function
relu
Show All
Embeds
Plots
Explanation
Show Test Field
Default Test Text
IFrame
<iframe src=https://www.neuronpedia.org/gemma-2b/12-res-jb/7870?embed=true&embedexplanation=true&embedplots=true&embedtest=true" title="Neuronpedia" style="height: 300px; width: 540px;"></iframe>
Link
https://www.neuronpedia.org/gemma-2b/12-res-jb/7870?embed=true&embedexplanation=true&embedplots=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Neuron Alignment
Index
Value
% of L₁
50
+0.30
1.0%
1978
+0.17
0.6%
678
+0.11
0.4%
Correlated Neurons
Index
P. Corr.
Cos Sim.
981
+0.30
0.09
304
+0.17
-0.01
1978
+0.11
0.08
Negative Logits
↵↵
-0.82
↵
-0.79
in
-0.79
、
-0.79
-0.78
and
-0.78
on
-0.77
-0.77
-0.76
-0.76
POSITIVE LOGITS
viciss
1.86
Sén
1.83
seksi
1.81
mef
1.80
Souha
1.80
panik
1.73
sappi
1.72
fta
1.71
fup
1.69
Bibl
1.68
Act
ivations
Density 0.912%
Stacked
Snippet
Full
Show Breaks
Hide Breaks
No Known Activations
