© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 8536
    Prev
    Next
    INDEX
    Explanations

    technical terms related to fluid dynamics and physical interactions in systems

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

    terms related to fluid dynamics and flow patterns in scientific contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    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
    TypedDataSet
    -0.50
     EconPapers
    -0.46
    InitVars
    -0.46
    acamata
    -0.45
     Chbosky
    -0.45
    chaun
    -0.44
    vų
    -0.42
     angesch
    -0.42
    Tracce
    -0.41
    ïsme
    -0.41
    POSITIVE LOGITS
     flow
    0.50
     convection
    0.44
     fluid
    0.42
     FixedUpdate
    0.42
     turbulent
    0.41
     Flow
    0.40
    endcsname
    0.40
     piloto
    0.39
     surface
    0.39
     turbul
    0.39
    Activations Density 0.473%

    No Known Activations