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. 16-GEMMASCOPE-RES-16K
    6. 3144
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to routing in programming or web development contexts

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

    "route" or "routes"

    np_acts-logits-general · gemini-2.0-flash

    route or circuit

    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
    olsom
    -0.82
    msford
    -0.80
     Folsom
    -0.74
    IntegerField
    -0.67
     Chrift
    -0.66
     ſmall
    -0.66
    gameserver
    -0.66
     وتسجيلات
    -0.64
     bezeichneter
    -0.63
     donnés
    -0.62
    POSITIVE LOGITS
     routes
    1.56
     Routes
    1.50
     Route
    1.48
     route
    1.44
    route
    1.37
    Route
    1.33
    Routes
    1.24
     ROUTE
    1.23
    routes
    1.22
    ROUTE
    1.15
    Activations Density 0.072%

    No Known Activations