Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 14431
    Prev
    Next
    INDEX
    Explanations

    layout and structure elements related to user interface design

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

    HTML table row `<tr>` tags

    np_acts-logits-general · gemini-2.0-flash

    layout structure

    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
    DockStyle
    -0.65
     SafeArea
    -0.59
    withIdentifier
    -0.59
    CardContent
    -0.59
    IndentedString
    -0.56
     EconPapers
    -0.56
    basicConfig
    -0.56
    ConstraintMaker
    -0.55
    Personensuche
    -0.54
     purpoſe
    -0.54
    POSITIVE LOGITS
    SequentialGroup
    0.68
    LayoutPanel
    0.39
    addRow
    0.36
    row
    0.36
    Wrk
    0.36
    HStack
    0.35
    BagLayout
    0.35
    tableLayoutPanel
    0.35
    flexDirection
    0.33
     row
    0.32
    Activations Density 0.038%

    No Known Activations