© 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. 5645
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    59.5
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    references to physical positioning and state changes

    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
    replacement
    -0.35
    Smarty
    -0.34
    andExpect
    -0.33
     infrastruktur
    -0.32
     replacement
    -0.31
     himo
    -0.31
    Infrastructure
    -0.30
     dredge
    -0.30
     superhuman
    -0.30
    Ehrungen
    -0.30
    POSITIVE LOGITS
     שוליים
    0.68
    fromnode
    0.67
    setVerticalGroup
    0.65
    ंदीखरीदारी
    0.60
    webElementXpaths
    0.56
    awtextra
    0.56
    ViewInit
    0.56
     للمعارف
    0.55
    transQ
    0.54
    +#+#
    0.54
    Activations Density 3.557%

    No Known Activations