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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 1101
    Prev
    Next
    INDEX
    Explanations

    mentions of physical activity or fitness-related activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Co-occurrences of locations/activities with prepositions

    np_acts-logits-general · gemini-2.0-flash

    specific locations or activities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    Referanser
    -0.52
     izvē
    -0.38
     initComponents
    -0.36
     Abschied
    -0.35
     Méndez
    -0.35
     banderas
    -0.34
     Ebene
    -0.34
     implements
    -0.34
     szint
    -0.34
    calientes
    -0.33
    POSITIVE LOGITS
     BoxFit
    0.58
     dunes
    0.53
    AndEndTag
    0.52
     dAtA
    0.51
     Snack
    0.50
     intran
    0.50
     messes
    0.50
     gigs
    0.49
    DoubleQuotes
    0.49
     playtime
    0.48
    Activations Density 0.141%

    No Known Activations