© 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. 2157
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    64
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    punctuation marks, particularly question marks and ellipses, indicating uncertainty or questioning

    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
     Wikimedijinoj
    -0.53
    celotti
    -0.53
    tyimages
    -0.47
    querque
    -0.47
    ☸
    -0.46
    SPARENT
    -0.46
     biologic
    -0.45
    iální
    -0.45
    estacks
    -0.45
    prefixer
    -0.45
    POSITIVE LOGITS
     maybe
    0.55
     might
    0.49
     Maybe
    0.48
    maybe
    0.48
    ########.
    0.47
     Could
    0.44
     possa
    0.44
     may
    0.41
     Might
    0.41
     måske
    0.41
    Activations Density 0.000%

    No Known Activations