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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 5492
    Prev
    Next
    INDEX
    Explanations

    contractions and possessive forms in text

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

    Android or custom kernels

    np_acts-logits-general · gemini-2.0-flash

    android and mobile devices

    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
    routeProvider
    -0.61
    ReadKey
    -0.60
    StoryboardSegue
    -0.60
     Macintosh
    -0.58
     Ferris
    -0.57
     AudioClip
    -0.56
    ftagPool
    -0.55
     BoxFit
    -0.54
     vhs
    -0.53
    makeConstraints
    -0.53
    POSITIVE LOGITS
     Android
    1.08
    Android
    0.95
     android
    0.94
    android
    0.86
     rooted
    0.78
    droid
    0.74
    rooted
    0.73
    ANDROID
    0.72
    Droid
    0.71
     Samsung
    0.70
    Activations Density 0.277%

    No Known Activations