© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-9B-IT
    5. 20-AXBENCH-REFT-R1-RES-16K
    7. 592
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    56
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    punctuation marks and sentence delimiters

    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
    DCHECK
    -0.35
     little
    -0.33
    )
    -0.32
     fully
    -0.31
     nawr
    -0.31
    \
    -0.30
     theoretical
    -0.29
     unrivalled
    -0.28
    reszcie
    -0.28
    ),
    -0.28
    POSITIVE LOGITS
     noDo
    0.70
     betweenstory
    0.67
     purpoſe
    0.67
     AssemblyCompany
    0.67
     verſch
    0.66
    <unused28>
    0.65
    <unused43>
    0.65
    <unused47>
    0.65
    <unused68>
    0.65
    <unused74>
    0.65
    Activations Density 1.680%

    No Known Activations