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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 4303
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to quantum field theory and renormalization

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

    complex mathematical and physics notation, particularly terms related to quantum mechanics, physics equations, and scientific notation.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    scientific or mathematical terms and concepts in technical/academic papers.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    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
     مشين
    -0.65
     للمعارف
    -0.61
    ➋
    -0.58
    ConfigureAwait
    -0.52
    EDEFAULT
    -0.52
    OGND
    -0.50
     estekak
    -0.49
     isNameExpr
    -0.47
    AppMethodBeat
    -0.45
     Phry
    -0.45
    POSITIVE LOGITS
     hidratante
    0.43
    ViewImports
    0.42
     peuple
    0.41
     účast
    0.41
     datter
    0.41
     식
    0.40
     zemi
    0.40
     spørsmål
    0.39
     partage
    0.39
    żyć
    0.39
    Activations Density 1.792%

    No Known Activations