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. 20-GEMMASCOPE-RES-16K
    6. 15470
    Prev
    Next
    INDEX
    Explanations

    specific geographical locations or organization names.

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

    technical terms related to academic research and publications.

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    references to locations, particularly cities and states in the United States, with a focus on St. Louis, Missouri and other Midwestern locations.

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @bot

    Missouri locations and abbreviations

    np_acts-logits-general · gemini-2.0-flash

    St. Louis, MO

    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
     EconPapers
    -0.85
    __;
    -0.75
    parsedMessage
    -0.75
    WEBPACK
    -0.71
    ScopeManager
    -0.69
    endphp
    -0.67
     estekak
    -0.67
     Luzon
    -0.62
     }{@
    -0.60
    Hentet
    -0.60
    POSITIVE LOGITS
     Missouri
    1.18
    Missouri
    1.04
     MO
    0.96
     STL
    0.86
    MO
    0.79
     Ozark
    0.74
     MISS
    0.72
    STL
    0.71
     Mo
    0.69
    OURI
    0.67
    Activations Density 0.280%

    No Known Activations