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
    39.25
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    occurrences of variable assignments and coding structures in programming discussions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ↵
    -0.33
    v
    -0.30
     aside
    -0.30
     replacement
    -0.30
    )
    -0.29
     Förderung
    -0.28
    
    -0.28
    )))),
    -0.27
     Aside
    -0.27
     Agricultura
    -0.27
    POSITIVE LOGITS
     nakalista
    0.76
     propOrder
    0.69
    transQ
    0.68
    rrggbb
    0.66
     autorytatywna
    0.66
     betweenstory
    0.64
    setVerticalGroup
    0.63
    səhifə
    0.62
    BufferException
    0.61
    TemporalType
    0.61
    Act Density 4.671%

    No Known Activations