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. 1222
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    39.25
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    punctuation marks and 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
     pungkas
    -0.41
     
    -0.38
     nawr
    -0.32
    )
    -0.32
    as
    -0.29
     Sw
    -0.29
     hatta
    -0.28
    -
    -0.28
    ]
    -0.28
     or
    -0.28
    POSITIVE LOGITS
    <pad>
    0.83
    <unused14>
    0.83
    <unused74>
    0.83
    [@BOS@]
    0.82
    <unused1>
    0.82
    <unused3>
    0.82
    <unused8>
    0.82
    <unused28>
    0.82
    <unused41>
    0.82
    <unused47>
    0.82
    Activations Density 1.819%

    No Known Activations