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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 1120
    Prev
    Next
    INDEX
    Explanations

    elements related to visual components or cards in UI design

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

    GUI elements: cards, boxes, rectangles

    np_acts-logits-general · gemini-2.0-flash

    UI elements and 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
    ########.
    -0.67
    getColumnIndex
    -0.59
    GraphicsUnit
    -0.58
    pexpr
    -0.58
    SequentialGroup
    -0.54
    RegistryLite
    -0.53
    IntoConstraints
    -0.52
     invokingState
    -0.50
    tagHelperRunner
    -0.50
    httphttps
    -0.50
    POSITIVE LOGITS
     groupBox
    0.54
    CardBody
    0.54
     building
    0.50
    GroupBox
    0.47
    CardView
    0.46
     CardView
    0.45
     door
    0.42
     structure
    0.42
    groupBox
    0.40
    building
    0.39
    Activations Density 0.063%

    No Known Activations