© 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. 4774
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    33.75
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    programming syntax elements and structure, particularly related to defining and using complex data structures and methods

    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
     AssemblyCulture
    -0.44
     peringatan
    -0.41
     juventud
    -0.40
     někdo
    -0.40
     Landwir
    -0.38
     čierna
    -0.38
     löytyy
    -0.38
     död
    -0.38
     yoksa
    -0.37
     penumpang
    -0.37
    POSITIVE LOGITS
    LayoutStyle
    0.61
     يتيمه
    0.61
    setVerticalGroup
    0.60
     Chu
    0.55
    Fel
    0.51
     propOrder
    0.51
    uxxxx
    0.51
    rrggbb
    0.50
     Fel
    0.50
     Clau
    0.50
    Activations Density 0.665%

    No Known Activations