© 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. 533
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    51
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    long sentences with authoritative tone or complex constructs

    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
    tanleria
    -0.57
     barata
    -0.46
    >')
    -0.45
    Smarty
    -0.43
    etcode
    -0.42
     baratos
    -0.40
    )»
    -0.40
     Extragalactic
    -0.40
    )».
    -0.39
     Debugging
    -0.39
    POSITIVE LOGITS
     resourceCulture
    0.52
    
    0.52
    InstrumentedTest
    0.49
     själ
    0.45
    ">//
    0.45
     propOrder
    0.44
    ViewInit
    0.43
    zä
    0.42
     nød
    0.42
     purpoſe
    0.42
    Activations Density 0.050%

    No Known Activations