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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-9B-IT
    3. 20-AXBENCH-REFT-R1-RES-16K
    4. 85
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    70.5
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    references to academic papers and collaborative research involving authors and institutions

    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
     Audiodateien
    -0.46
    moga
    -0.41
    replacement
    -0.40
     nguyên
    -0.40
     enormously
    -0.39
     replaces
    -0.39
     enormous
    -0.39
    法律
    -0.38
    pidou
    -0.38
     glittering
    -0.37
    POSITIVE LOGITS
    rungsseite
    0.47
    onViewCreated
    0.46
     authorship
    0.44
    authored
    0.43
    Chham
    0.43
     chercheurs
    0.42
    iastes
    0.42
     ſch
    0.42
     Administrativna
    0.42
     authors
    0.41
    Activations Density 0.036%

    No Known Activations