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
    50.5
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    punctuation markers and ellipses, indicating pauses or omissions in text

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    󠁣
    -0.48
    isième
    -0.43
    endente
    -0.42
     nawr
    -0.39
    bust
    -0.39
     gynhyrchwyd
    -0.38
    ocell
    -0.38
     Rousse
    -0.38
    orsese
    -0.38
    󠁢
    -0.38
    POSITIVE LOGITS
     betweenstory
    0.54
     CreateTagHelper
    0.52
     Taktlose
    0.51
    fromnode
    0.48
     ExecuteAsync
    0.47
    IntoConstraints
    0.45
    transQ
    0.45
    árbol
    0.43
    ########.
    0.43
     propOrder
    0.41
    Act Density 0.806%

    No Known Activations