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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 5086
    Prev
    Next
    INDEX
    Explanations

    specific legal terminology and phrases related to court proceedings

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

    Nautical terms and boat speeds

    np_acts-logits-general · gemini-2.0-flash

    boat speed | sea | wreckage

    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
    kmäler
    -0.63
     AssemblyCompany
    -0.60
     Hershey
    -0.54
     Burkina
    -0.53
    calientes
    -0.52
     Laramie
    -0.51
     Allentown
    -0.51
     Wolverhampton
    -0.50
    étaro
    -0.50
    ptonshire
    -0.49
    POSITIVE LOGITS
     marine
    1.25
     maritime
    1.16
     seawater
    1.16
     boats
    1.14
     sea
    1.13
     ashore
    1.09
     nautical
    1.08
     Marine
    1.07
     boat
    1.07
     offshore
    1.07
    Activations Density 1.448%

    No Known Activations