© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 100875
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to fluid dynamics and computational fluid dynamics (CFD)

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

    fluid dynamics simulations

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    ligkeit
    -0.45
    Referanser
    -0.44
    TypedDataSet
    -0.41
    izumi
    -0.41
    SharedCtor
    -0.41
    льність
    -0.40
     fotografico
    -0.40
    tvguidetime
    -0.40
     bulunabilir
    -0.40
     biß
    -0.39
    POSITIVE LOGITS
    ClCompile
    0.41
     FixedUpdate
    0.41
     hydrodynamic
    0.40
    endcsname
    0.38
     CFD
    0.38
    IsPostBack
    0.38
    toplankton
    0.37
     ſind
    0.36
     QtCore
    0.35
    ísica
    0.35
    Activations Density 0.085%

    No Known Activations