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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 120836
    Prev
    Next
    INDEX
    Explanations

    references to legal cases and their details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     iprot
    -0.68
    rungsseite
    -0.66
    keyColumn
    -0.64
     AssemblyCulture
    -0.63
     صوتيه
    -0.57
    تقاوى
    -0.56
    DockStyle
    -0.55
     lenker
    -0.54
    Tembelea
    -0.54
     kasarigan
    -0.53
    POSITIVE LOGITS
    orianCalendar
    0.43
    < 
    0.42
     Supplementary
    0.36
    Bioaccumulative
    0.34
    Supplementary
    0.33
    Vorte
    0.31
     entanto
    0.31
    gadier
    0.31
     Nevertheless
    0.29
    óloga
    0.29
    Activations Density 0.031%

    No Known Activations