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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 38250
    Prev
    Next
    INDEX
    Explanations

    occurrences of function definitions and method calls in programming code

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

    code syntax and structure

    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
    Personendaten
    -0.77
    featureID
    -0.68
    期刊论文
    -0.63
     ModelExpression
    -0.61
    verwijspagina
    -0.61
     }}"></
    -0.60
    fjspx
    -0.59
    :+:
    -0.59
    </tfoot>
    -0.57
    ScopeManager
    -0.57
    POSITIVE LOGITS
    hébergement
    0.38
     Öffnungszeiten
    0.35
     betweenstory
    0.35
    hånd
    0.35
    sedur
    0.32
     düş
    0.30
     konuş
    0.30
    Modifiers
    0.29
    delning
    0.29
    dik
    0.29
    Activations Density 0.074%

    No Known Activations