Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    30.75
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    instances of programming language constructs and syntax

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     
    -0.36
     gerais
    -0.35
     kandang
    -0.35
     edades
    -0.31
     be
    -0.30
     hitam
    -0.30
     Audiodateien
    -0.30
     dapur
    -0.29
     legais
    -0.28
     caminando
    -0.28
    POSITIVE LOGITS
     propOrder
    0.78
    Искәрмәләр
    0.76
    ValueStyle
    0.74
     nakalista
    0.73
    setVerticalGroup
    0.73
    Autoritní
    0.71
     transfieras
    0.71
     defaultstate
    0.71
    <unused3>
    0.69
    <unused23>
    0.69
    Act Density 2.997%

    No Known Activations