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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 4318
    Prev
    Next
    INDEX
    Explanations

    references to the city of San Antonio and related entities

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

    The token "San" followed by a capitalized word

    np_acts-logits-general · gemini-2.0-flash

    San place names and sanitization

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Roskov
    -0.76
    VIAF
    -0.75
     CommandType
    -0.72
     lenker
    -0.71
     Wikimedijinoj
    -0.71
     Galer
    -0.71
    usermodel
    -0.71
     CGPA
    -0.70
    nologue
    -0.70
    RenderAtEndOf
    -0.68
    POSITIVE LOGITS
     San
    1.12
     SAN
    1.04
    San
    1.02
     san
    0.93
    SAN
    0.93
    san
    0.83
     Sanford
    0.78
     Sandi
    0.78
     Sans
    0.77
     Sanctions
    0.76
    Activations Density 0.124%

    No Known Activations