© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 1601
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    36.25
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    punctuations and formatting that indicate text structure or begin a new section

    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
    v
    -0.31
     kako
    -0.29
    \
    -0.29
    )
    -0.27
    -
    -0.27
    ))^{
    -0.27
    w
    -0.27
     Landwir
    -0.26
    ))^
    -0.26
     replacement
    -0.26
    POSITIVE LOGITS
    
    0.91
    rrggbb
    0.77
     Administrativna
    0.77
     propOrder
    0.75
    BufferException
    0.75
    URLException
    0.75
    majánló
    0.74
     kasarigan
    0.73
    setVerticalGroup
    0.73
     betweenstory
    0.71
    Activations Density 3.081%

    No Known Activations