© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 1437
    Prev
    Next
    INDEX
    Explanations

    medical and biological terminology related to diseases and treatment methods

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

    Follows "a", "of", "the", "an", or "syndrome"

    np_acts-logits-general · gemini-2.0-flash

    introducing definitions

    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
     يتيمه
    -0.57
    RegressionTest
    -0.56
    ViewImports
    -0.55
     NSCoder
    -0.55
    .*")]
    -0.54
     ligiloj
    -0.49
    bron
    -0.47
     Induction
    -0.47
    StoryboardSegue
    -0.46
    SourceChecksum
    -0.46
    POSITIVE LOGITS
     autorytatywna
    0.55
    alakip
    0.42
    ceğine
    0.39
     informée
    0.38
     juſ
    0.37
    asList
    0.35
     faſt
    0.35
     worldwide
    0.34
     weltweit
    0.34
     surla
    0.34
    Activations Density 0.450%

    No Known Activations