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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-9B-IT
    3. 20-AXBENCH-REFT-R1-RES-16K
    4. 753
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    40
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    sentences and phrases that indicate quantitative assessments or summaries

    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
    -0.32
     пожалуйста
    -0.31
    interprétation
    -0.29
     nawr
    -0.28
    culadora
    -0.27
     vraiment
    -0.27
     peringatan
    -0.26
     miteinander
    -0.25
    reszcie
    -0.25
     Messung
    -0.25
    POSITIVE LOGITS
    BufferException
    0.75
    rrggbb
    0.65
    MessageTagHelper
    0.64
     beſti
    0.64
    <unused15>
    0.63
    bibfield
    0.63
    <unused1>
    0.63
     purpoſe
    0.63
    <unused3>
    0.63
    <unused7>
    0.63
    Activations Density 2.420%

    No Known Activations