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. 874
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    49.75
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    numerical values or measurements

    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
     switch
    -0.38
    wood
    -0.37
    )
    -0.36
    switch
    -0.34
    st
    -0.31
     
    -0.30
    ):
    -0.30
     little
    -0.30
     fully
    -0.30
    >
    -0.30
    POSITIVE LOGITS
     AssemblyCompany
    0.75
     насељу
    0.75
     betweenstory
    0.74
    
    0.73
    ſelf
    0.73
     purpoſe
    0.70
     propOrder
    0.69
     noDo
    0.68
    ContentAlignment
    0.68
     itſelf
    0.68
    Activations Density 1.629%

    No Known Activations