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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-9B-IT
    3. 20-AXBENCH-REFT-R1-RES-16K
    4. 5596
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    91.5
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    phrases related to object instantiation and singleton patterns in a programming context

    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
    WireFormatLite
    -0.38
    Hochspringen
    -0.35
     dasarnya
    -0.33
    ratulations
    -0.33
     wichtiger
    -0.32
     hakim
    -0.32
    祝
    -0.31
    ongiorno
    -0.30
     "").
    -0.30
     offizi
    -0.30
    POSITIVE LOGITS
    verifyException
    0.76
     متعلقه
    0.59
     للمعارف
    0.56
     Theron
    0.53
     autorytatywna
    0.53
    /*
    0.52
     يتيمه
    0.52
    optionalTypeArgs
    0.52
     صوتيه
    0.52
     singleton
    0.51
    Activations Density 0.064%

    No Known Activations