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
    39
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    references to programming and code structures

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     pungkas
    -0.38
     kullanım
    -0.30
     
    -0.30
     mevcut
    -0.27
    retudo
    -0.27
     expectativa
    -0.27
     belakang
    -0.27
    /
    -0.27
    iestety
    -0.26
     communauté
    -0.25
    POSITIVE LOGITS
    <unused41>
    0.83
    <unused74>
    0.83
    [@BOS@]
    0.83
    <unused1>
    0.83
    <unused3>
    0.83
    <unused8>
    0.83
    <unused14>
    0.83
    <unused17>
    0.83
    <unused23>
    0.83
    <unused28>
    0.83
    Act Density 6.333%

    No Known Activations