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-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 11178
    Prev
    Next
    INDEX
    Explanations

    references to Asia and its influence in various contexts

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

    "Asia" or "Asian"

    np_acts-logits-general · gemini-2.0-flash

    Asia Pacific, Asian Americans

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MigrationBuilder
    -0.58
    preventDefault
    -0.51
     Normdatei
    -0.50
    ########.
    -0.49
     دیکھیے
    -0.47
    homonymie
    -0.46
     nasional
    -0.45
     federally
    -0.45
     nationale
    -0.45
    illite
    -0.45
    POSITIVE LOGITS
     countries
    1.17
     Countries
    0.99
     COUNTRIES
    0.90
    countries
    0.89
     BoxFit
    0.88
     region
    0.87
    Countries
    0.83
     länder
    0.81
     nations
    0.79
     Tenggara
    0.79
    Activations Density 0.146%

    No Known Activations