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-2-9B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 5585
    Prev
    Next
    INDEX
    Explanations

    locations and descriptions of hospital facilities

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

    Multiple locations or branches

    np_acts-logits-general · gemini-2.0-flash

    locations and their scope

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sprzed
    -0.31
    modelBuilder
    -0.30
    Underlying
    -0.30
    harusnya
    -0.30
    sell
    -0.30
     arbete
    -0.30
     slä
    -0.29
     förm
    -0.29
     Piro
    -0.29
    Biografía
    -0.29
    POSITIVE LOGITS
     locations
    0.99
     sites
    0.83
     Locations
    0.82
     depots
    0.79
    Locations
    0.79
     everywhere
    0.79
     centres
    0.77
     places
    0.77
     nationwide
    0.77
     LOCATIONS
    0.76
    Activations Density 0.517%

    No Known Activations