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 - 65k
    5. 20-GEMMASCOPE-RES-65K
    6. 952
    Prev
    Next
    INDEX
    Explanations

    temperature measurements

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

    temperature values and related measurements

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

    temperature in Celsius

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     autorytatywna
    -0.72
     propOrder
    -0.71
     AssemblyTitle
    -0.68
     ویکی‌پدیای
    -0.67
     تضيفلها
    -0.67
    MigrationBuilder
    -0.67
    ViewFeatures
    -0.66
     مرئيه
    -0.63
     resourceCulture
    -0.63
    TestBed
    -0.63
    POSITIVE LOGITS
    C
    0.60
     C
    0.59
    illère
    0.52
    F
    0.50
     Celsius
    0.47
    caler
    0.46
     avenge
    0.46
     F
    0.46
    sand
    0.46
    setCharacter
    0.46
    Activations Density 0.029%

    No Known Activations