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
    53.5
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    function definitions in code snippets

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     někdo
    -0.42
     AssemblyCulture
    -0.40
    WriteTagHelper
    -0.40
     preocupes
    -0.37
     cucharadita
    -0.37
     strå
    -0.36
     Stimmung
    -0.36
     setelan
    -0.35
    లాలు
    -0.35
     Unterkunft
    -0.35
    POSITIVE LOGITS
     propOrder
    0.68
    InstrumentedTest
    0.59
    LayoutStyle
    0.54
    cupa
    0.54
     Qui
    0.54
     Rockefeller
    0.53
    Hoc
    0.53
     AVC
    0.53
    
    0.53
     Ul
    0.52
    Act Density 0.076%

    No Known Activations