© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-9B-IT
    5. 20-AXBENCH-REFT-R1-RES-16K
    7. 203
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    42
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    distinct sentence structures or punctuation patterns, particularly focusing on variation in sentence endings and use of special characters

    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
    tagext
    -0.34
     totul
    -0.28
     peringatan
    -0.28
     opravdu
    -0.27
     fama
    -0.27
     legais
    -0.26
    reszcie
    -0.26
     
    -0.26
     iar
    -0.26
    Smarty
    -0.26
    POSITIVE LOGITS
     purpoſe
    0.69
    évaluateur
    0.66
    setVerticalGroup
    0.65
    ftance
    0.64
     betweenstory
    0.63
    ſelves
    0.62
    BufferException
    0.61
    <unused1>
    0.60
    <unused6>
    0.60
    <unused3>
    0.60
    Activations Density 1.701%

    No Known Activations