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. 5-GEMMASCOPE-RES-16K
    6. 3768
    Prev
    Next
    INDEX
    Explanations

    terms related to routing and route definitions in web applications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    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
    -0.98
     وتسجيلات
    -0.89
    ictus
    -0.82
     Folsom
    -0.79
     DevComponents
    -0.77
     FIM
    -0.76
     Timor
    -0.76
    eclared
    -0.75
    ApiModelProperty
    -0.75
     Herak
    -0.75
    POSITIVE LOGITS
     routes
    2.37
     route
    2.32
     Route
    2.19
     Routes
    2.12
    route
    2.07
    Route
    2.06
     ROUTE
    1.90
    Routes
    1.86
    routes
    1.76
    ROUTE
    1.72
    Activations Density 0.039%

    No Known Activations