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
    57
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    code related to Python functions and syntax

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     uzak
    -0.33
     conocemos
    -0.31
     někdo
    -0.30
     wiadomo
    -0.29
     menilai
    -0.29
     hendes
    -0.28
     wichtiger
    -0.28
     länger
    -0.28
     celebrado
    -0.28
     allgemeinen
    -0.28
    POSITIVE LOGITS
    ThroughAttribute
    0.78
    rrggbb
    0.76
     Administrativna
    0.71
    Искәрмәләр
    0.69
     propOrder
    0.68
    WithIOException
    0.68
    <pad>
    0.67
    <unused3>
    0.67
    <unused15>
    0.67
    <unused1>
    0.66
    Act Density 0.001%

    No Known Activations