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. 2758
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    58
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    technical metrics and rigorous analysis frameworks in research contexts

    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
    ⎨
    -0.51
     وتسجيلات
    -0.43
    WriteTagHelper
    -0.43
     vendido
    -0.40
    SPATH
    -0.40
    tanleria
    -0.39
     mwaka
    -0.39
     viewWillAppear
    -0.38
    onghi
    -0.38
    étoit
    -0.38
    POSITIVE LOGITS
    LookAnd
    0.66
    fromnode
    0.52
    PreExecute
    0.52
    InstrumentedTest
    0.51
     šte
    0.50
    setVerticalGroup
    0.50
     Савезне
    0.46
     score
    0.46
     Normdatei
    0.44
    worthiness
    0.42
    Activations Density 0.026%

    No Known Activations