© 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-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 113090
    Prev
    Next
    INDEX
    Explanations

    conditional compilation directives in programming code

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

    closing conditional compilation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    yarnpkg
    -0.90
     ſei
    -0.87
    帖最后由
    -0.86
     ſondern
    -0.79
     ſua
    -0.78
    ſicht
    -0.76
    niſſe
    -0.75
     beſte
    -0.75
     ſoll
    -0.75
     ſehr
    -0.75
    POSITIVE LOGITS
    endif
    1.46
    endregion
    0.99
     endif
    0.50
    !
    0.48
     endregion
    0.44
    .
    0.42
    .*;
    0.42
    ?
    0.41
     This
    0.40
    ENDIF
    0.40
    Activations Density 0.007%

    No Known Activations