© 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. 13191
    Prev
    Next
    INDEX
    Explanations

    XML and layout-related components in code

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

    XML/layout panel or linear layout

    np_acts-logits-general · gemini-2.0-flash

    UI layout elements

    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
    kháu
    -0.55
    EndInit
    -0.53
    BeginInit
    -0.47
    InjectAttribute
    -0.46
     հղումներ
    -0.46
    +#+
    -0.45
     wiesz
    -0.41
    tvguidetime
    -0.41
    ształ
    -0.41
    issory
    -0.40
    POSITIVE LOGITS
    BagLayout
    0.66
     JPanel
    0.61
    JPanel
    0.60
    LayoutPanel
    0.58
    ConstraintLayout
    0.58
    BoxLayout
    0.57
     GridLayout
    0.57
    LinearLayout
    0.54
    GridLayout
    0.53
    SafeAreaView
    0.52
    Activations Density 0.196%

    No Known Activations