© 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
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 6265
    Prev
    Next
    INDEX
    Explanations

    Android layout and view configuration terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     demografica
    -0.47
    internalType
    -0.43
    WebVitals
    -0.39
    InjectAttribute
    -0.38
     породы
    -0.36
    asal
    -0.35
    +#+
    -0.35
     pinulongan
    -0.34
    prüfung
    -0.34
    impôt
    -0.34
    POSITIVE LOGITS
    RelativeLayout
    0.96
    ConstraintLayout
    0.90
    LayoutPanel
    0.89
     RelativeLayout
    0.85
    FrameLayout
    0.76
    LinearLayout
    0.76
     LinearLayout
    0.73
     JPanel
    0.73
    ViewGroup
    0.72
     jPanel
    0.71
    Activations Density 0.236%

    No Known Activations