© 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. 3720
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    34.75
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    syntactical structures and comments often found in programming code

    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
     nawr
    -0.44
     pungkas
    -0.41
     miteinander
    -0.39
    ByVersion
    -0.36
    <bos>
    -0.34
    Aholisi
    -0.34
    retudo
    -0.33
    Hochspringen
    -0.32
     tarz
    -0.32
     getItemId
    -0.31
    POSITIVE LOGITS
    bibfield
    0.55
    transQ
    0.55
    rrggbb
    0.55
    
    0.55
     Hollande
    0.53
    tvguidetime
    0.52
     OSP
    0.52
    IntoConstraints
    0.52
    uxxxx
    0.51
     TPP
    0.51
    Activations Density 0.805%

    No Known Activations