© 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. 15477
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to lithography and its components

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

    technical or scientific notation, particularly in mathematical expressions and programming code.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    technical STEM notation and jargon, especially LaTeX/math symbols, acronyms, and code-like identifiers in scientific or programming contexts.

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

    the definite article "the" in technical or scientific text.

    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
    ParseTree
    -0.33
    Rhestr
    -0.31
    niająca
    -0.30
    PasswordEncoder
    -0.30
     precum
    -0.30
     biru
    -0.29
     Dernière
    -0.29
    انجليز
    -0.28
     Keny
    -0.28
     asesinado
    -0.27
    POSITIVE LOGITS
     الحره
    0.72
    يكب
    0.60
     esternos
    0.57
    writeFieldEnd
    0.56
    principalTable
    0.55
     nakalista
    0.55
     lenker
    0.54
    UnifiedTopology
    0.54
     مشين
    0.54
    期刊论文
    0.53
    Activations Density 1.093%

    No Known Activations