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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 12266
    Prev
    Next
    INDEX
    Explanations

    references to governmental structures and societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     celle
    -0.57
     quoi
    -0.50
     student
    -0.49
    excellents
    -0.49
     Student
    -0.47
    ไล
    -0.47
    cad
    -0.45
     celles
    -0.45
     celui
    -0.45
    student
    -0.45
    POSITIVE LOGITS
    IntoConstraints
    0.85
    ViewImports
    0.77
    таратура
    0.76
     isInitialized
    0.73
    chequer
    0.70
    PerformLayout
    0.69
    atschappij
    0.68
    TestingModule
    0.68
     externi
    0.67
    rungsseite
    0.66
    Activations Density 0.784%

    No Known Activations