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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 9219
    Prev
    Next
    INDEX
    Explanations

    LaTeX formatting and commands, particularly related to geometry and document structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    stylesheet
    -0.70
    
    -0.60
    usepackage
    -0.54
    CppMethod
    -0.54
    MigrationBuilder
    -0.52
    IBOutlet
    -0.51
     nonUne
    -0.51
    ChildScrollView
    -0.50
    SequentialGroup
    -0.48
    WEBPACK
    -0.47
    POSITIVE LOGITS
    [
    0.62
    -[
    0.43
     tren
    0.41
     integrator
    0.40
    [-
    0.40
    󠁢
    0.39
     $[
    0.39
     igjen
    0.39
     separator
    0.38
    WithFormat
    0.38
    Activations Density 0.122%

    No Known Activations