© 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. 18-GEMMASCOPE-RES-16K
    11. 4080
    Prev
    Next
    INDEX
    Explanations

    references to towns and their governmental or community structures

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

    "Town" or "town"

    np_acts-logits-general · gemini-2.0-flash

    town hall or town of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     timing
    -1.00
     Timing
    -0.83
     pinulongan
    -0.82
    Timing
    -0.74
    timing
    -0.70
     Winaray
    -0.69
     timed
    -0.68
    ificantly
    -0.64
     untimely
    -0.64
     Vertra
    -0.63
    POSITIVE LOGITS
    AsUp
    0.84
    Towns
    0.81
     Towns
    0.72
    towns
    0.72
     TOWNS
    0.69
     towns
    0.68
     головой
    0.68
     Townsend
    0.67
     Towne
    0.67
     Town
    0.63
    Activations Density 0.037%

    No Known Activations