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. 7521
    Prev
    Next
    INDEX
    Explanations

    references to seismic events, particularly earthquakes and their measurements

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

    Earthquakes and seismic activity

    np_acts-logits-general · gemini-2.0-flash

    earthquake seismic magnitude

    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
    lowy
    -0.41
     pican
    -0.41
     tulisan
    -0.41
     Hoog
    -0.40
     Xerox
    -0.40
    CrossRef
    -0.40
    Ո
    -0.40
    trá
    -0.40
    cektir
    -0.40
    לק
    -0.39
    POSITIVE LOGITS
     earthquake
    1.55
     earthquakes
    1.37
     Earthquake
    1.35
    Earthquake
    1.25
     quake
    1.20
     seismic
    1.16
     seismo
    1.15
     Earthquakes
    1.13
     Seismic
    1.11
    quakes
    1.09
    Activations Density 0.082%

    No Known Activations