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. 1074
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    75.5
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    references to programming languages, libraries, or tools used in software development

    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
    WriteTagHelper
    -0.72
    Personendaten
    -0.65
    GEBURTSDATUM
    -0.61
    assertRaises
    -0.56
    findpost
    -0.54
    GTCX
    -0.52
    UnusedPrivate
    -0.52
     Paglinawan
    -0.51
     Italijanski
    -0.50
    المناصب
    -0.50
    POSITIVE LOGITS
     normas
    0.44
     standards
    0.43
     sort
    0.38
     conventions
    0.38
     normes
    0.36
     rules
    0.35
    közi
    0.35
     pourtant
    0.34
     estándares
    0.34
     configurations
    0.34
    Activations Density 0.003%

    No Known Activations