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. 7-GEMMASCOPE-RES-16K
    6. 15174
    Prev
    Next
    INDEX
    Explanations

    references to the United States in the context of governance or policy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     defaultstate
    -0.86
     alder
    -0.80
     Tafel
    -0.79
     Chernobyl
    -0.77
    elemField
    -0.77
    InjectAttribute
    -0.76
    RegressionTest
    -0.73
     Thumbnails
    -0.72
     Alderman
    -0.72
     Mardi
    -0.71
    POSITIVE LOGITS
     US
    1.50
    US
    1.23
     USA
    1.22
     States
    1.17
     United
    1.06
     STATES
    0.99
     states
    0.95
     Us
    0.93
     American
    0.92
    USA
    0.91
    Activations Density 0.149%

    No Known Activations