© 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. 1796
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    70
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    instances of repetition and recurrence in various forms

    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
    Personendaten
    -0.62
    aguay
    -0.43
    Certificates
    -0.43
    doria
    -0.43
    IMPORTANT
    -0.42
    rometry
    -0.42
     <>",
    -0.40
    RemoveField
    -0.40
    atrician
    -0.40
    jardins
    -0.40
    POSITIVE LOGITS
     repeated
    0.59
     wiederhol
    0.59
     repeti
    0.57
     repetition
    0.57
     repetir
    0.56
     ripet
    0.55
     répé
    0.52
     repeat
    0.52
     wiederholt
    0.50
     repetitive
    0.50
    Activations Density 0.005%

    No Known Activations