Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 2911
    Prev
    Next
    INDEX
    Explanations

    geographical references and locations within a city context

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

    "Liverpool"

    np_acts-logits-general · gemini-2.0-flash

    Liverpool places and universities

    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
     initComponents
    -0.86
     Lesotho
    -0.81
     Laramie
    -0.72
    참고
    -0.66
     MASSACHUSETTS
    -0.64
     Butte
    -0.63
    tvguidetime
    -0.62
    kloped
    -0.61
    windowFixed
    -0.60
     Boulder
    -0.60
    POSITIVE LOGITS
     Liverpool
    1.02
    Liverpool
    0.93
     Merseyside
    0.85
     LIVER
    0.79
     Anfield
    0.75
     Mersey
    0.72
     liverpool
    0.68
     Klopp
    0.67
     Liver
    0.66
     ECHO
    0.63
    Activations Density 0.142%

    No Known Activations