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. 6607
    Prev
    Next
    INDEX
    Explanations

    importantes regarding native plants in relation to ecological restoration

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

    gardens, farms, or function variables

    np_acts-logits-general · gemini-2.0-flash

    garden, plants, farm

    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
    StructEnd
    -0.75
    SharedCtor
    -0.59
    omitempty
    -0.58
    bufio
    -0.56
    openSession
    -0.55
     كومونز
    -0.55
    DoubleQuotes
    -0.54
    Oneof
    -0.54
    DrawerToggle
    -0.53
    HandlerContext
    -0.53
    POSITIVE LOGITS
     garden
    1.82
     gardening
    1.68
     gardens
    1.63
     gardeners
    1.54
     plants
    1.46
     gardener
    1.45
     Garden
    1.44
    garden
    1.43
     Gardening
    1.40
    Garden
    1.38
    Activations Density 0.200%

    No Known Activations