© 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. 3282
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    28.875
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    references to legal or regulatory provisions

    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
     
    -0.31
     condena
    -0.27
    )
    -0.27
    <bos>
    -0.26
     conmemor
    -0.25
     réglage
    -0.25
     off
    -0.25
     hatta
    -0.25
     eigentlich
    -0.24
    anniversaire
    -0.24
    POSITIVE LOGITS
     betweenstory
    0.91
     Normdatei
    0.87
     propOrder
    0.82
    
    0.82
    transQ
    0.80
    évaluateur
    0.77
    <unused3>
    0.71
    <pad>
    0.70
    <unused8>
    0.70
    <unused14>
    0.70
    Activations Density 3.333%

    No Known Activations