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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 3751
    Prev
    Next
    INDEX
    Explanations

    references to the app within various contexts, particularly in configuration and usage scenarios

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

    "app" or "App" token

    np_acts-logits-general · gemini-2.0-flash

    app

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
     OMIT
    -0.55
     ".",
    -0.52
     ""),
    -0.52
     ".";
    -0.50
     Sinai
    -0.50
    |)
    -0.50
     "");
    -0.50
    vind
    -0.50
     "";
    -0.49
    withCredentials
    -0.49
    POSITIVE LOGITS
    App
    1.12
     App
    1.11
     APP
    1.05
     app
    1.00
    APP
    0.99
    getApp
    0.96
     Apps
    0.95
    app
    0.94
    sApp
    0.93
     getApp
    0.90
    Activations Density 0.059%

    No Known Activations