© 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. 8854
    Prev
    Next
    INDEX
    Explanations

    references to universities and higher education institutions

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

    structured, data-heavy academic formatting—especially LaTeX-style math and tables with dense sequences of numbers, decimals, and scores often accompanying affiliations or author lists.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    tabular data with numeric rankings, scores, or measurements, particularly in academic or scientific contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    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
     surla
    -0.48
    liceerd
    -0.41
     schoenen
    -0.40
     évolution
    -0.39
    nezeu
    -0.39
    ChildScrollView
    -0.37
     obuv
    -0.37
    UserScript
    -0.37
     Mejora
    -0.37
     tenisky
    -0.36
    POSITIVE LOGITS
     <<<<<<<<<<<<<<
    0.65
     AssemblyProduct
    0.48
     ویکی‌پدیا
    0.42
    ⓧ
    0.40
    Anmeldung
    0.36
     newBuilder
    0.35
     역
    0.34
    OB
    0.34
     autorytatywna
    0.34
    éz
    0.34
    Activations Density 0.180%

    No Known Activations