Neuronpedia
Get Started
API
Releases
Jump To
Search
Models
Assistant Axis
NEW
Circuit Tracer
NEW
Steer
SAE Evals
Exports
Community
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
20-GEMMASCOPE-RES-16K
1438
Prev
Next
MODEL
20-gemmascope-res-16k
Source/SAE
INDEX
Go
Explanations
equations and mathematical expressions related to functions and variables.
oai_token-act-pair · gpt-4o-mini
Triggered by @bot
Avg Score: 95
mathematical equations and symbols in a technical context.
oai_token-act-pair · gpt-3.5-turbo
Triggered by @bot
Avg Score: 95
mathematical expressions and equations, particularly those involving fractions, trigonometric functions, and Greek letters.
oai_token-act-pair · claude-3-5-sonnet-20240620
Triggered by @bot
Avg Score: 89
Mathematical expressions with pi
np_acts-logits-general · gemini-2.0-flash
No Scores
mathematical pi
np_acts-logits-general · gemini-2.5-flash-lite
No Scores
New Auto-Interp
AutoInterp Type
claude-4-5-haiku
Generate
Top Features by Cosine Similarity
Comparing With
GEMMA-2-2B @ 20-gemmascope-res-16k
Configuration
google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
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.20.hook_resid_post
Hook Layer
20
Architecture
jumprelu
Context Size
1,024
Dataset
monology/pile-uncopyrighted
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-2-2b/20-gemmascope-res-16k/1438?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-2-2b/20-gemmascope-res-16k/1438?embed=true&embedexplanation=true&embedplots=true&embedsteer=true&embedactivations=true&embedlink=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Negative Logits
Sort
-0.52
medios
-0.50
ubro
-0.49
Sort
-0.49
θεν
-0.48
gæ
-0.46
Bully
-0.46
porcentual
-0.46
/\.
-0.45
ilidad
-0.45
POSITIVE LOGITS
pi
1.18
π
1.15
pi
1.14
π
1.10
PI
1.07
PI
1.05
Pi
1.03
𝜋
0.84
0.84
Pi
0.82
Act
ivations
Density 0.568%
Test
Steer
Stacked
Snippet
Full
Show Raw Tokens
Show Formatted
Show Breaks
Hide Breaks
No Known Activations
