© 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. 563
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    42.75
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    citations or references in a text

    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
     nawr
    -0.38
    tagext
    -0.37
     wypo
    -0.31
    WireFormat
    -0.30
     hatta
    -0.28
     Negra
    -0.28
     wirklich
    -0.28
     deuil
    -0.28
    <bos>
    -0.28
     güneş
    -0.28
    POSITIVE LOGITS
     betweenstory
    0.63
    
    0.58
    Autoritní
    0.55
     CanadaChoose
    0.54
    richTextPanel
    0.53
    setVerticalGroup
    0.52
    ftance
    0.52
     purpoſe
    0.52
     bezeichneter
    0.51
     насељу
    0.51
    Activations Density 5.578%

    No Known Activations