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
    56.5
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    punctuation marks, particularly question marks and periods

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     vapour
    -0.39
     bonded
    -0.36
     fertiliser
    -0.36
     recognised
    -0.35
    off
    -0.34
     feud
    -0.33
     renown
    -0.33
     provavelmente
    -0.33
     practised
    -0.33
     probably
    -0.33
    POSITIVE LOGITS
    PerformLayout
    0.56
    fromnode
    0.53
     defaultstate
    0.51
     jScrollPane
    0.51
     AdapterView
    0.51
    addCriterion
    0.50
     CreateTagHelper
    0.49
    Manbalar
    0.49
    /**
    0.49
     bezeichneter
    0.49
    Act Density 0.222%

    No Known Activations