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. 5290
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    75
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    references to various types of analyses and methodologies in scientific 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
    WriteTagHelper
    -0.61
     SYLLABLE
    -0.50
    Personendaten
    -0.49
    bootstrapcdn
    -0.44
    Smarty
    -0.44
    ⟺
    -0.43
    __).
    -0.43
    )»
    -0.42
    oluble
    -0.42
    ⎨
    -0.42
    POSITIVE LOGITS
    InstrumentedTest
    0.54
     testing
    0.50
     test
    0.49
     methodology
    0.47
     measurement
    0.47
    TestMethod
    0.46
     laboratory
    0.46
     Guinée
    0.45
     methodologies
    0.44
     tests
    0.44
    Activations Density 0.056%

    No Known Activations