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-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 6609
    Prev
    Next
    INDEX
    Explanations

    concerns related to extracellular matrix remodeling and collagen synthesis

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

    Extracellular matrix and related molecules

    np_acts-logits-general · gemini-2.0-flash

    extracellular matrix components

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
    •Marfan Syndrome
    Marfan Syndrome

    No Comments

    Negative Logits
     externi
    -0.75
     linkovi
    -0.70
    WebElementEntity
    -0.68
    Personensuche
    -0.67
     insectic
    -0.64
     برانيه
    -0.63
    Einzelnachweise
    -0.62
     Paglinawan
    -0.61
     candlestick
    -0.61
     ***!
    -0.60
    POSITIVE LOGITS
     collagen
    1.03
     Collagen
    0.88
     matrix
    0.84
     connective
    0.77
     Matrix
    0.76
     ECM
    0.75
     fib
    0.75
    matrix
    0.72
    Col
    0.70
    Matrix
    0.70
    Activations Density 0.992%

    No Known Activations