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
    47
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    technical terminology and specific variable names

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     
    -0.37
    st
    -0.30
    assertRaises
    -0.28
    )
    -0.28
    령
    -0.28
    ]
    -0.28
     short
    -0.27
    \
    -0.27
     beliau
    -0.27
    <eos>
    -0.26
    POSITIVE LOGITS
    0.75
    rrggbb
    0.73
    ſelves
    0.71
    Tikang
    0.71
    transQ
    0.70
     propOrder
    0.70
     ſche
    0.68
     purpoſe
    0.68
     initComponents
    0.67
     ſta
    0.65
    Act Density 6.298%

    No Known Activations