© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-9B-IT
    3. 20-AXBENCH-REFT-R1-RES-16K
    4. 404
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    44.5
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    mathematical notations and equations related to statistical or computational concepts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    pyvene/gemma-reft-r1-9b-it-res/l20
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tanleria
    -0.31
     Toen
    -0.29
     hug
    -0.28
    zarchiwizowane
    -0.28
     switch
    -0.27
    Switch
    -0.27
     adulte
    -0.27
    揄
    -0.27
    isième
    -0.26
    הערות
    -0.26
    POSITIVE LOGITS
    LookAnd
    0.77
    setVerticalGroup
    0.69
    
    0.66
     queſta
    0.64
    ſelf
    0.63
     ComVisible
    0.59
    SystemColors
    0.59
    fromnode
    0.57
    basicConfig
    0.56
     betweenstory
    0.56
    Activations Density 2.424%

    No Known Activations