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. 16-GEMMASCOPE-RES-16K
    6. 12227
    Prev
    Next
    INDEX
    Explanations

    terms related to the measurement of earthquakes and seismic activity

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

    earthquakes or geology

    np_acts-logits-general · gemini-2.0-flash

    geological activity

    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
    nteral
    -0.58
     Plas
    -0.55
    Lähteet
    -0.53
    UMBUS
    -0.52
     quyết
    -0.48
     staining
    -0.48
     maximization
    -0.48
    VITA
    -0.47
    Inters
    -0.47
    otá
    -0.47
    POSITIVE LOGITS
     earthquake
    0.98
    quakes
    0.92
     earthquakes
    0.91
     seismo
    0.83
     Seismic
    0.80
     Earthquake
    0.78
     seismic
    0.78
     geologists
    0.77
     quake
    0.73
     geologist
    0.73
    Activations Density 0.122%

    No Known Activations