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. 13780
    Prev
    Next
    INDEX
    Explanations

    terms associated with biological processes and movement of substances in blood and tissues

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

    Prepositions followed by locations in the body/environment

    np_acts-logits-general · gemini-2.0-flash

    into locations and environments

    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
    Not in Any Lists

    No Comments

    Negative Logits
     ModelExpression
    -0.57
    IntoConstraints
    -0.56
     Waray
    -0.54
    Jegyzetek
    -0.46
    ">//
    -0.45
    AddHtmlAttribute
    -0.45
     continúas
    -0.44
    fjspx
    -0.44
     timur
    -0.43
    tiéndose
    -0.43
    POSITIVE LOGITS
     tissues
    0.91
     atmosphere
    0.91
     bloodstream
    0.89
     airspace
    0.82
     surroundings
    0.81
     tissus
    0.80
     cytoplasm
    0.78
     environment
    0.74
     surrounding
    0.72
     tejidos
    0.71
    Activations Density 1.117%

    No Known Activations