© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-9B-IT
    5. 20-AXBENCH-REFT-R1-RES-16K
    7. 2943
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    38.25
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    metadata and formatting cues in the document

    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
    reszcie
    -0.34
     hatta
    -0.32
    tagext
    -0.29
    eseorang
    -0.28
     ***!
    -0.28
     hijau
    -0.28
    iestety
    -0.28
    ConstraintMaker
    -0.28
     
    -0.28
     başar
    -0.28
    POSITIVE LOGITS
    ftance
    0.65
    rrggbb
    0.63
    
    0.62
    ſelves
    0.60
    ſelf
    0.59
     queſta
    0.59
     beſti
    0.58
     EnglishChoose
    0.57
     purpoſe
    0.57
    Хьажоргаш
    0.57
    Activations Density 1.187%

    No Known Activations