© 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. 9-GEMMASCOPE-RES-16K
    11. 9924
    Prev
    Next
    INDEX
    Explanations

    equations and expressions related to physical laws and principles in fluid dynamics

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

    physics and mathematics terminology related to equations, conservation laws, and physical properties of systems.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    WebElementEntity
    -0.49
     ModelExpression
    -0.47
    BeginContext
    -0.44
     CallOverrides
    -0.43
     ویکی‌پدیا
    -0.42
    getBean
    -0.42
    intios
    -0.41
    клопе
    -0.41
    يكب
    -0.41
    orsch
    -0.41
    POSITIVE LOGITS
     princí
    0.41
     redacción
    0.38
     isSelected
    0.38
    oweit
    0.37
     kasarigan
    0.37
     espé
    0.36
    徹底
    0.35
     dopln
    0.35
     Thermodynamics
    0.35
     přístup
    0.35
    Activations Density 1.367%

    No Known Activations