© 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. 3545
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    63.25
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    the name "Luther" and related character names, indicating a focus on specific individuals in a narrative context

    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
     AssemblyCulture
    -0.68
    :✨
    -0.56
    WriteTagHelper
    -0.52
    Parcelize
    -0.49
     Вікі
    -0.48
    arangay
    -0.47
    EDEFAULT
    -0.46
     Gegenteil
    -0.45
    новниш
    -0.44
    商品説明
    -0.44
    POSITIVE LOGITS
     dilemmas
    0.47
     relationships
    0.44
     encounters
    0.41
    /*
    0.40
    èvres
    0.38
     JAXB
    0.38
     challenges
    0.37
     Guinée
    0.37
     Relationships
    0.36
     himself
    0.36
    Activations Density 0.000%

    No Known Activations