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. 135
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    60.75
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    academic papers or studies that focus on analysis and validation of research findings

    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
     Wikimedijinoj
    -0.72
     himo
    -0.71
     AssemblyCulture
    -0.68
    :✨
    -0.62
    WriteTagHelper
    -0.59
    raulic
    -0.57
     rhestr
    -0.55
     وتسجيلات
    -0.55
    IndentedString
    -0.55
    redient
    -0.54
    POSITIVE LOGITS
     kajian
    0.45
     analysis
    0.41
     study
    0.38
     discussion
    0.38
     evaluation
    0.38
     examining
    0.38
     evaluar
    0.38
     análisis
    0.37
     étudi
    0.37
    텐츠
    0.37
    Activations Density 0.017%

    No Known Activations