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

    Neuronpedia

    Jacobian LensNEW
    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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 103844
    Prev
    Next
    INDEX
    Explanations

    technical terms and jargon related to software, hardware, and computational systems

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

    Acronyms or abbreviations for technical tools, software, programming languages, or computing concepts that appear in technical or scientific documentation.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    appui
    -0.36
    htä
    -0.34
     Grunde
    -0.33
    .
    -0.32
     whole
    -0.32
    1
    -0.31
     przeci
    -0.29
    0
    -0.29
     ganzen
    -0.29
    chodzi
    -0.29
    POSITIVE LOGITS
    featureID
    0.92
     المعيارى
    0.88
     kasarigan
    0.81
    parsedMessage
    0.80
    RegressionTest
    0.79
    WithIOException
    0.78
    ंदीखरीदारी
    0.77
     فريبيس
    0.76
    دانشنامهٔ
    0.73
    jspb
    0.72
    Activations Density 0.829%

    No Known Activations