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 2026
Privacy & Terms
Blog
GitHub
Slack
Twitter
Contact
Home
Google DeepMind · Exploring Gemma 2 with Gemma Scope
Gemma-2-2B
Residual Stream - 65k
13-GEMMASCOPE-RES-65K
38758
Prev
Next
MODEL
13-gemmascope-res-65k
Source/SAE
INDEX
Go
Explanations
key terms related to technical specifications and classifications
oai_token-act-pair · gpt-4o-mini
Triggered by @bot
No Scores
New Auto-Interp
AutoInterp Type
claude-4-5-haiku
Generate
Top Features by Cosine Similarity
Comparing With
GEMMA-2-2B @ 13-gemmascope-res-65k
Configuration
google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
How To Load
Prompts (Dashboard)
24,576 prompts, 128 tokens each
Dataset (Dashboard)
monology/pile-uncopyrighted
Features
65,536
Data Type
float32
Hook Name
blocks.13.hook_resid_post
Hook Layer
13
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/13-gemmascope-res-65k/38758?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/13-gemmascope-res-65k/38758?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
itſelf
-1.45
myſelf
-1.42
doubtnut
-1.40
$_(
-1.37
Efq
-1.35
ſelves
-1.31
ſeveral
-1.27
ſelf
-1.24
$_"
-1.24
iſt
-1.17
POSITIVE LOGITS
,
1.53
)
1.28
1.28
1.09
]
1.08
}
1.04
:
1.01
!
1.01
;
0.99
),
0.99
Act
ivations
Density 1.187%
Stacked
Snippet
Full
Show Raw Tokens
Show Formatted
Show Breaks
Hide Breaks
No Known Activations
