© 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. 4087
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    31.25
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    references to specific organizations, plans, or structured data related to professional or formal contexts

    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
     off
    -0.35
    ):
    -0.31
    off
    -0.30
     
    -0.29
    le
    -0.28
    -
    -0.28
     missão
    -0.28
    ].
    -0.27
     Messung
    -0.26
    )
    -0.26
    POSITIVE LOGITS
     propOrder
    0.81
    rrggbb
    0.79
    évaluateur
    0.69
    transQ
    0.68
    <pad>
    0.67
    <unused1>
    0.66
    <unused14>
    0.66
    <unused41>
    0.66
    <unused47>
    0.66
    <unused51>
    0.66
    Activations Density 8.526%

    No Known Activations