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. 1159
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    59.5
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    instances of strong positive or affirmative sentiments and endorsements

    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
     theoretically
    -0.40
    DCHECK
    -0.36
     ***!
    -0.36
     theoretical
    -0.34
     hipó
    -0.34
    Smarty
    -0.32
    最重要
    -0.32
    HttpFoundation
    -0.31
    theoretical
    -0.31
    first
    -0.30
    POSITIVE LOGITS
     resourceCulture
    0.65
    rrggbb
    0.59
     betweenstory
    0.59
    setVerticalGroup
    0.59
    InstrumentedTest
    0.57
    LookAnd
    0.54
    webElementXpaths
    0.53
    ">//
    0.53
    ValueStyle
    0.52
    +#+#
    0.51
    Activations Density 4.802%

    No Known Activations