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
    75.5
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    mentions of "memories."

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     AssemblyCulture
    -0.65
    bootstrapcdn
    -0.59
    bewerken
    -0.56
    WriteTagHelper
    -0.56
     grosso
    -0.54
    нгред
    -0.54
     hydra
    -0.52
    openqa
    -0.51
    AddTagHelper
    -0.51
    IntoConstraints
    -0.50
    POSITIVE LOGITS
     memories
    0.60
     remembering
    0.51
     recalling
    0.51
     reminis
    0.49
     recalled
    0.48
     lembran
    0.47
     remembered
    0.47
     recalls
    0.46
     recollections
    0.45
     Erinnerungen
    0.45
    Act Density 0.000%

    No Known Activations