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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-9B-IT
    5. 20-AXBENCH-REFT-R1-RES-16K
    7. 4064
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    56.75
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    topics related to academic research and discourse

    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
    TacToe
    -0.42
     batter
    -0.40
     Tinto
    -0.38
     _)
    -0.37
    thical
    -0.37
    grine
    -0.37
    httphttps
    -0.37
     switch
    -0.37
     Switch
    -0.37
    >')
    -0.37
    POSITIVE LOGITS
    ViewInit
    0.52
     himſelf
    0.51
    enumii
    0.47
    ंदीखरीदारी
    0.47
     purpoſe
    0.46
     propOrder
    0.46
     Contoh
    0.44
    LEGGI
    0.42
     AssemblyCompany
    0.41
    bibfield
    0.41
    Activations Density 2.907%

    No Known Activations