© 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. 7476
    Prev
    Next
    INDEX
    Explanations

    concepts related to empirical results and analysis in scientific research

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

    scientific or technical terms related to measurement, data, or research findings.

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

    technical, research-oriented terminology typical of scholarly articles, especially words denoting measurements, results, models, bounds, and formal methodology.

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

    technical or academic language, particularly in scientific and research contexts discussing methodologies, results, parameters, and theoretical frameworks.

    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
     Савезне
    -0.52
     насељу
    -0.52
    +:+
    -0.50
    HasAnnotation
    -0.50
     Италијани
    -0.49
     виправивши
    -0.49
    stylers
    -0.46
    ंदीखरीदारी
    -0.45
     GoogleFonts
    -0.45
    DockStyle
    -0.45
    POSITIVE LOGITS
     seriously
    0.45
     beyond
    0.41
     Lipp
    0.41
     similar
    0.40
     Covering
    0.39
     covering
    0.39
    WebServlet
    0.38
     rest
    0.38
     مشين
    0.37
     Brun
    0.37
    Activations Density 1.238%

    No Known Activations