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
Google DeepMind · Exploring Gemma 2 with Gemma Scope
Gemma-2-2B
Residual Stream - 16k
5-GEMMASCOPE-RES-16K
12304
Prev
Next
MODEL
5-gemmascope-res-16k
Source/SAE
INDEX
Go
Explanations
instances of the letter 'u' in various contexts
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
Comparing With
GEMMA-2-2B @ 5-gemmascope-res-16k
Configuration
google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
How To Load
Prompts (Dashboard)
36,864 prompts, 128 tokens each
Dataset (Dashboard)
monology/pile-uncopyrighted
Features
16,384
Data Type
float32
Hook Name
blocks.5.hook_resid_post
Hook Layer
5
Architecture
jumprelu
Context Size
1,024
Dataset
monology/pile-uncopyrighted
Activation Function
relu
Show All
Embeds
Plots
Explanation
Show Test Field
Default Test Text
IFrame
<iframe src=https://www.neuronpedia.org/gemma-2-2b/5-gemmascope-res-16k/12304?embed=true&embedexplanation=true&embedplots=true&embedtest=true" title="Neuronpedia" style="height: 300px; width: 540px;"></iframe>
Link
https://www.neuronpedia.org/gemma-2-2b/5-gemmascope-res-16k/12304?embed=true&embedexplanation=true&embedplots=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Negative Logits
Theſe
-0.83
dring
-0.74
Anſ
-0.73
―――――
-0.72
truff
-0.72
corrid
-0.72
་་
-0.71
Beſ
-0.71
Camin
-0.69
الشر
-0.69
POSITIVE LOGITS
u
1.88
U
1.67
U
1.43
u
1.25
uve
1.02
v
1.00
V
0.98
ｕ
0.93
l
0.93
r
0.91
Act
ivations
Density 0.098%
Test
Steer
Stacked
Snippet
Full
Show Breaks
Hide Breaks
No Known Activations
