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
    50.75
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    references to incomplete thoughts or segments of text that indicate continuation or ellipsis

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    󠁴
    -0.53
     fertiliser
    -0.48
     referenties
    -0.48
    newArrayList
    -0.48
     vapour
    -0.48
    揄
    -0.47
    angas
    -0.47
    Hochspringen
    -0.47
    jure
    -0.46
     nawr
    -0.46
    POSITIVE LOGITS
    fromnode
    0.38
     achtergrond
    0.37
    árbol
    0.37
     wikipagina
    0.37
    ContentAlignment
    0.34
     целях
    0.34
     purposes
    0.34
    rrggbb
    0.34
     Japão
    0.34
     propósitos
    0.34
    Act Density 0.553%

    No Known Activations