© 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-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 1211
    Prev
    Next
    INDEX
    Explanations

    references to mobile applications and their features

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

    "app", "apk", and "android"

    np_acts-logits-general · gemini-2.0-flash

    app store and android apks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
    parsedMessage
    -0.68
     فريبيس
    -0.66
    enderror
    -0.57
    SequentialGroup
    -0.56
     Phong
    -0.56
    posedge
    -0.55
     MyBatis
    -0.55
    بوابة
    -0.54
     Henson
    -0.54
    TagHelper
    -0.53
    POSITIVE LOGITS
     Android
    1.19
     APK
    1.13
     apk
    1.13
     android
    1.07
    apk
    1.04
    Android
    1.03
    android
    0.96
     Apk
    0.93
     App
    0.92
     app
    0.90
    Activations Density 0.331%

    No Known Activations