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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 1-GEMMASCOPE-RES-16K
    6. 9306
    Prev
    Next
    INDEX
    Explanations

    references to America

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    abancı
    -0.58
     Zwick
    -0.57
     esper
    -0.53
    ibal
    -0.53
    izations
    -0.53
    Belle
    -0.52
     Wiktionnaire
    -0.52
    nonce
    -0.51
     Schi
    -0.51
    Mater
    -0.51
    POSITIVE LOGITS
     America
    2.12
    America
    2.06
     AMERICA
    1.90
     america
    1.74
    america
    1.57
     Americas
    1.00
    CloseOperation
    0.99
    americas
    0.98
    Americas
    0.95
     América
    0.92
    Activations Density 0.059%

    No Known Activations