Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-9B-IT
    3. 20-AXBENCH-REFT-R1-RES-16K
    4. 2696
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    43
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    mathematical notations and symbols

    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
    )
    -0.37
     
    -0.36
    <eos>
    -0.35
    ):
    -0.33
    -
    -0.29
     kick
    -0.28
     off
    -0.28
    )
    -0.28
     )
    -0.28
     '
    -0.28
    POSITIVE LOGITS
    rrggbb
    1.00
     propOrder
    0.93
    
    0.86
     Administrativna
    0.82
     kasarigan
    0.80
     autorytatywna
    0.80
    Tikang
    0.72
     '\\;'
    0.72
    setVerticalGroup
    0.72
     ſehen
    0.70
    Activations Density 3.778%

    No Known Activations