© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 283
    Prev
    Next
    INDEX
    Explanations

    place names, particularly cities and states in the United States

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

    Cities (Kansas City, New York, Oklahoma City)

    np_acts-logits-general · gemini-2.0-flash

    city names followed by City

    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
    jooq
    -0.64
    KommentareTeilen
    -0.63
     Photocase
    -0.60
    IndentedString
    -0.55
    Попис
    -0.54
    ząt
    -0.53
    anganronpa
    -0.52
    ècie
    -0.52
    Diwedd
    -0.51
    SdkVersion
    -0.50
    POSITIVE LOGITS
     City
    2.71
    City
    2.32
     CITY
    2.18
    CITY
    1.75
    city
    1.75
     city
    1.69
    シティ
    1.24
     getCity
    1.18
     Metropolis
    1.16
    getCity
    1.15
    Activations Density 0.147%

    No Known Activations