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. 21-GEMMASCOPE-RES-16K
    6. 8483
    Prev
    Next
    INDEX
    Explanations

    phrases and references related to governmental structures and entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ">//
    -0.64
     Empieza
    -0.59
    contentLoaded
    -0.56
     StatefulWidget
    -0.54
    InjectAttribute
    -0.53
     Азии
    -0.53
     Europy
    -0.51
     <<<<<<<<<<<<<<
    -0.49
     الرياضيه
    -0.48
    جغرافيا
    -0.48
    POSITIVE LOGITS
     Republic
    1.22
     republic
    1.00
    Republic
    0.95
     REPUBLIC
    0.87
     United
    0.82
     Federal
    0.79
     Republik
    0.74
    republic
    0.74
     People
    0.73
     république
    0.73
    Activations Density 0.296%

    No Known Activations