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. 5015
    Prev
    Next
    INDEX
    Explanations

    references to the Earth and its related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    NamedQueries
    -0.58
    titleMargin
    -0.56
     anticip
    -0.56
    gemar
    -0.56
     Infórmanos
    -0.56
    RenderAtEndOf
    -0.56
    BeginInit
    -0.55
     conspic
    -0.55
    idemia
    -0.54
    windowFixed
    -0.54
    POSITIVE LOGITS
     EARTH
    0.75
    EARTH
    0.69
     Earth
    0.66
    worm
    0.65
     Erde
    0.63
    shaking
    0.63
     planète
    0.62
    worms
    0.61
     earth
    0.60
    quakes
    0.59
    Activations Density 0.072%

    No Known Activations