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-IT SAEs
Gemma-2B-IT
Residual Stream
12-RES-JB
15398
Prev
Next
MODEL
12-res-jb
Source/SAE
INDEX
Go
Explanations
quotes and narratives given by different individuals
oai_token-act-pair · gpt-3.5-turbo
Triggered by @bot
No Scores
New Auto-Interp
AutoInterp Type
claude-4-5-haiku
Generate
Top Features by Cosine Similarity
Configuration
jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_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
float32
Hook Name
blocks.12.hook_resid_post
Hook Layer
12
Architecture
standard
Context Size
1,024
Dataset
Skylion007/openwebtext
Activation Function
relu
Show All
Embeds
Show Plots
Show Explanation
Show Activations
Show Test Field
Show Steer
Show Link
IFrame
<iframe src="https://www.neuronpedia.org/gemma-2b-it/12-res-jb/15398?embed=true&embedexplanation=true&embedplots=true&embedsteer=true&embedactivations=true&embedlink=true&embedtest=true" title="Neuronpedia" style="height: 300px; width: 540px;"></iframe>
Link
https://www.neuronpedia.org/gemma-2b-it/12-res-jb/15398?embed=true&embedexplanation=true&embedplots=true&embedsteer=true&embedactivations=true&embedlink=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Neuron Alignment
Index
Value
% of L₁
1974
+0.13
0.4%
381
+0.12
0.4%
1510
+0.11
0.4%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1637
+0.13
0.07
1974
+0.12
0.08
521
+0.11
0.07
Negative Logits
thuy
-0.84
Nguy
-0.71
kinh
-0.71
chuy
-0.66
nguyen
-0.65
nuoc
-0.61
marcato
-0.60
tuong
-0.60
Nguy
-0.59
phan
-0.59
POSITIVE LOGITS
He
0.98
he
0.89
He
0.85
She
0.79
he
0.78
she
0.77
HE
0.73
HE
0.71
himself
0.68
She
0.66
Act
ivations
Density 0.403%
Stacked
Snippet
Full
Show Raw Tokens
Show Formatted
Show Breaks
Hide Breaks
No Known Activations
