© 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. 30-GEMMASCOPE-RES-16K
    11. 12278
    Prev
    Next
    INDEX
    Explanations

    pieces of code or HTML tags associated with navigation elements

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

    Code related to toolbars and bars

    np_acts-logits-general · gemini-2.0-flash

    navigation bars and toolbars

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    contentLoaded
    -0.65
    ContentAsync
    -0.52
    ClCompile
    -0.49
     مواليد
    -0.47
     /\.
    -0.47
     mouseClicked
    -0.46
     TType
    -0.46
    ModelForm
    -0.46
    ReusableCell
    -0.45
    NameInMap
    -0.45
    POSITIVE LOGITS
     bar
    0.88
     toolbar
    0.83
    bar
    0.72
     Toolbar
    0.71
     bars
    0.68
     navbar
    0.68
    menuStrip
    0.67
    Bar
    0.66
     Navbar
    0.64
     Bar
    0.63
    Activations Density 0.259%

    No Known Activations