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. 16334
    Prev
    Next
    INDEX
    Explanations

    references to locations and their features, particularly in urban development contexts

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

    following "is", "and", "from", "on", or numbers

    np_acts-logits-general · gemini-2.0-flash

    island locations

    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
     OREGON
    -0.46
    kela
    -0.46
     Shasta
    -0.46
     trein
    -0.46
     Ethiopia
    -0.45
    Ethiopia
    -0.45
    ADELPHIA
    -0.45
     Swarm
    -0.44
    ABAD
    -0.43
     colombiano
    -0.43
    POSITIVE LOGITS
     islanders
    0.92
     island
    0.88
     Island
    0.82
     Guernsey
    0.79
    Island
    0.78
     تضيفلها
    0.78
     Islanders
    0.77
     autorytatywna
    0.75
     }{@
    0.74
     propOrder
    0.73
    Activations Density 0.078%

    No Known Activations