Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 23863
    Prev
    Next
    INDEX
    Explanations

    keywords related to historical and political contexts, particularly those associated with the Civil War and abolitionism

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

    German states and regions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     surla
    -0.60
    contentLoaded
    -0.58
    InputBorder
    -0.56
    ьаж
    -0.55
    principalColumn
    -0.52
    Ecotoxicity
    -0.50
     насељу
    -0.50
    Tikang
    -0.46
     ویکی‌پدی
    -0.46
     Савезне
    -0.45
    POSITIVE LOGITS
     Unitarian
    0.37
     usine
    0.35
     Gere
    0.33
     Union
    0.33
     Catalog
    0.32
     katalog
    0.32
     Unions
    0.32
     reform
    0.32
     Katalog
    0.32
    gms
    0.31
    Activations Density 0.061%

    No Known Activations