© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-9B-IT
    5. 20-AXBENCH-REFT-R1-RES-16K
    7. 6149
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    5.125
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    references to specific individuals and their actions or attributes

    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
     naturel
    -0.39
    Ecotoxicity
    -0.39
    oltà
    -0.39
     CascadeType
    -0.36
    TypedDataSet
    -0.36
     sinn
    -0.36
    GIVEREF
    -0.35
     simb
    -0.34
     TType
    -0.32
     myſelf
    -0.32
    POSITIVE LOGITS
    webElementXpaths
    0.68
    الحياه
    0.68
     المعيارى
    0.66
    CppCodeGen
    0.60
    delwed
    0.56
    Tikang
    0.55
    findpost
    0.53
    complexType
    0.49
     ProtoMessage
    0.48
     szóci
    0.45
    Activations Density 0.048%

    No Known Activations