© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 10782
    Prev
    Next
    INDEX
    Explanations

    references to routes or routing concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    parsedMessage
    -0.66
    oredCriteria
    -0.57
    ⓘ
    -0.54
     MainAxisSize
    -0.52
    AccessorTable
    -0.49
     dAtA
    -0.49
    MessageOf
    -0.49
    UnusedPrivate
    -0.45
    UnknownFieldSet
    -0.43
    ChildScrollView
    -0.43
    POSITIVE LOGITS
    Route
    3.64
     Route
    3.59
     route
    3.52
    route
    3.39
     ROUTE
    3.17
     routes
    2.83
    ROUTE
    2.78
     Routes
    2.72
    routes
    2.39
    Routes
    2.39
    Activations Density 0.073%

    No Known Activations