© 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. 2629
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    29.5
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    programming-related language constructs and syntax

    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
     miteinander
    -0.33
     locura
    -0.29
     Políticas
    -0.28
     penyel
    -0.27
    ]}
    -0.26
    brigens
    -0.26
     arrivare
    -0.25
     cintura
    -0.25
     terbang
    -0.24
     dönüş
    -0.24
    POSITIVE LOGITS
     تضيفلها
    0.75
     Administrativna
    0.73
     kasarigan
    0.72
    rrggbb
    0.71
    Билгалдахарш
    0.69
    transQ
    0.69
     للاسماء
    0.69
    <unused1>
    0.68
    <unused3>
    0.68
    <unused8>
    0.68
    Activations Density 7.812%

    No Known Activations