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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-9B-IT
    5. 20-AXBENCH-REFT-R1-RES-16K
    7. 572
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    39.5
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    phrases or terms associated with facts, evidence, or data, especially in a formal or academic 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
    tagext
    -0.40
    Personendaten
    -0.38
     świ
    -0.38
     başar
    -0.36
     itinéraires
    -0.35
     nawr
    -0.32
     
    -0.32
     thưởng
    -0.32
     său
    -0.32
     AssemblyCulture
    -0.31
    POSITIVE LOGITS
    ſelf
    0.61
    MigrationBuilder
    0.61
     betweenstory
    0.60
    setVerticalGroup
    0.60
    ſelves
    0.60
    <unused1>
    0.59
     يتيمه
    0.59
    <unused8>
    0.58
    <unused14>
    0.58
    <unused28>
    0.58
    Activations Density 2.475%

    No Known Activations