© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 108952
    Prev
    Next
    INDEX
    Explanations

    symbols and notations commonly used in programming or mathematical expressions

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

    API endpoints or URLs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    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
     meubles
    -0.33
     coroa
    -0.33
     rainha
    -0.32
     dieux
    -0.32
     enfans
    -0.31
     Fitz
    -0.31
     Pan
    -0.30
     Segurança
    -0.29
     âmes
    -0.29
     chiens
    -0.29
    POSITIVE LOGITS
    RegressionTest
    1.33
     linkovi
    1.09
    NameInMap
    1.09
     Савезне
    1.03
     Италијани
    1.01
    évaluateur
    0.95
    EndGlobalSection
    0.94
    الدراسه
    0.94
    Datuak
    0.91
    MigrationBuilder
    0.91
    Activations Density 0.001%

    No Known Activations