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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 57956
    Prev
    Next
    INDEX
    Explanations

    specific coding or programming terms associated with data processing or syntax

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

    intervention or technical terms

    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
     Roskov
    -0.47
     informée
    -0.47
    insegna
    -0.43
    MigrationBuilder
    -0.42
     '\\;'
    -0.41
     PagesJaunes
    -0.35
    ICHE
    -0.33
     contactez
    -0.33
     Baillargeon
    -0.32
    ICED
    -0.31
    POSITIVE LOGITS
    Chham
    0.62
     ligiloj
    0.62
     الرياضيه
    0.53
     старости
    0.50
    principalColumn
    0.50
    MethodManager
    0.49
    PreExecute
    0.49
    новниш
    0.47
    avigation
    0.47
    beforeEach
    0.46
    Activations Density 0.641%

    No Known Activations