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
228
Prev
Next
MODEL
12-res-jb
Source/SAE
INDEX
Go
Explanations
terms related to historical or technical descriptions of artifacts or items
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/228?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/228?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
1699
+0.14
0.4%
658
+0.10
0.3%
906
+0.10
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1524
+0.14
0.03
227
+0.10
0.04
543
+0.10
0.03
Negative Logits
pamph
-0.94
viciss
-0.90
źródło
-0.86
Примеча
-0.85
Prí
-0.84
Dijo
-0.84
Ży
-0.83
Zalety
-0.80
Había
-0.79
Leurs
-0.78
POSITIVE LOGITS
(
1.47
(
1.31
(
1.11
((
0.99
($
0.99
("
0.96
((
0.92
([
0.92
(
0.90
('
0.89
Act
ivations
Density 0.194%
Stacked
Snippet
Full
Show Raw Tokens
Show Formatted
Show Breaks
Hide Breaks
No Known Activations