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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-9B-IT
    3. 20-AXBENCH-REFT-R1-RES-16K
    4. 752
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    71
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    words related to emotional states or feelings

    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
    zeera
    -0.58
    bootstrapcdn
    -0.52
     theoretically
    -0.48
    tdb
    -0.48
    
    -0.47
    publique
    -0.47
     ویکی‌پدیای
    -0.47
     Jazeera
    -0.47
    WriteTagHelper
    -0.46
    $_['
    -0.46
    POSITIVE LOGITS
     joyful
    0.54
     enjoyment
    0.48
     joy
    0.48
    Enjoy
    0.48
    enjoy
    0.48
     enjoy
    0.47
    ValueStyle
    0.46
     enjoyed
    0.45
     joyfully
    0.45
     moments
    0.45
    Activations Density 0.000%

    No Known Activations