© 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-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 779
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to programming and API usage

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

    Code, paths, or routes

    np_acts-logits-general · gemini-2.0-flash

    router, route

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    twimg
    -0.84
     pido
    -0.46
     McCra
    -0.45
     JTextArea
    -0.43
     thermoc
    -0.43
     sł
    -0.42
    icap
    -0.41
    cías
    -0.41
     mornings
    -0.41
    ení
    -0.41
    POSITIVE LOGITS
     route
    1.32
     Route
    1.32
    router
    1.25
    Router
    1.25
    Route
    1.23
    route
    1.19
     router
    1.18
     Router
    1.18
     ROUTE
    1.17
     routes
    1.13
    Activations Density 0.087%

    No Known Activations