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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 5121
    Prev
    Next
    INDEX
    Explanations

    technical terms related to vehicle towing and coupling mechanisms

    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
     ujednoznacz
    -0.78
     forceps
    -0.77
    تقاوى
    -0.74
    Filmographie
    -0.68
    QMetaType
    -0.68
     disambiguazione
    -0.66
    quiao
    -0.66
    ViewImports
    -0.65
     ivelany
    -0.62
    iseau
    -0.62
    POSITIVE LOGITS
     camp
    1.62
     camping
    1.60
     campers
    1.48
     camper
    1.47
     campground
    1.45
    camp
    1.43
     Camping
    1.41
     campsite
    1.36
     Camp
    1.32
    camping
    1.32
    Activations Density 0.076%

    No Known Activations