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
    40
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    instances of high activation values indicating significant points of interest or importance in a document

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    WriteTagHelper
    -0.44
     peringatan
    -0.41
     bubuk
    -0.38
     AssemblyCulture
    -0.37
     nawr
    -0.37
     hendes
    -0.35
     juridiques
    -0.34
    <bos>
    -0.34
     kõik
    -0.34
     medži
    -0.33
    POSITIVE LOGITS
     propOrder
    0.62
    BufferException
    0.59
    0.58
    stdc
    0.53
    Искәрмәләр
    0.53
    DebuggerStep
    0.52
    rrggbb
    0.52
    setVerticalGroup
    0.51
    bibfield
    0.51
    SourceChecksum
    0.50
    Act Density 0.004%

    No Known Activations