© 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. 3690
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    78.5
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    references to input devices or interactions

    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
    zarchiwizowane
    -0.44
     Rechnung
    -0.37
    期刊论文
    -0.36
    |}
    -0.35
     Bigger
    -0.35
     nieruch
    -0.35
    )}}
    -0.34
     Probable
    -0.34
     rowspan
    -0.34
    Hochspringen
    -0.34
    POSITIVE LOGITS
    PerformLayout
    0.68
    RenderAtEndOf
    0.59
     keyboard
    0.57
    Билгалдахарш
    0.54
    Chham
    0.53
     teclado
    0.52
    FormState
    0.52
     TextInput
    0.48
    IUrlHelper
    0.48
    fromnode
    0.48
    Activations Density 0.000%

    No Known Activations