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
    37
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    code snippets and programming-related terms

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     peringatan
    -0.37
     
    -0.31
     panggilan
    -0.31
    Personendaten
    -0.29
     miteinander
    -0.29
     Exteriores
    -0.29
     başarı
    -0.29
     ***!
    -0.28
     fully
    -0.28
     verantwortlich
    -0.28
    POSITIVE LOGITS
     propOrder
    0.68
    <unused1>
    0.64
    <unused28>
    0.64
    <unused41>
    0.64
    <pad>
    0.63
    <unused3>
    0.63
    <unused8>
    0.63
    <unused14>
    0.63
    <unused51>
    0.63
    <unused52>
    0.63
    Act Density 9.631%

    No Known Activations