© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 20-GEMMASCOPE-RES-65K
    6. 1321
    Prev
    Next
    INDEX
    Explanations

    programming-related keywords and data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    coding-related terms and functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    asking questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     transfieras
    -0.67
     يتيمه
    -0.62
    '=>$
    -0.54
     nahilalakip
    -0.53
    %";
    -0.53
     nor
    -0.51
     Nor
    -0.50
    "=>$
    -0.50
    spyOn
    -0.50
    nextInt
    -0.49
    POSITIVE LOGITS
    ?
    1.31
    /?
    1.05
    ؟
    0.97
    ?
    0.94
    ?_
    0.92
    }?
    0.91
    ?&
    0.89
     ?
    0.88
    %?
    0.87
    ?"
    0.85
    Activations Density 0.054%

    No Known Activations