© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-9B-IT
    5. 20-AXBENCH-REFT-R1-RES-16K
    7. 1791
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    57.75
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    references to content types and headers in HTTP responses

    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
    assertRaises
    -0.41
    instancetype
    -0.35
     
    -0.34
     Audiodateien
    -0.34
    WireFormat
    -0.33
     onlyOwner
    -0.31
    〕
    -0.30
    ɵɵelementEnd
    -0.28
    Personendaten
    -0.28
     kandang
    -0.28
    POSITIVE LOGITS
     propOrder
    0.83
    səhifə
    0.64
     nakalista
    0.60
    .*")]
    0.60
     صوتيه
    0.57
    <unused1>
    0.56
    <pad>
    0.55
    <unused8>
    0.55
    <unused28>
    0.55
    <unused41>
    0.55
    Activations Density 0.251%

    No Known Activations