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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 15639
    Prev
    Next
    INDEX
    Explanations

    concepts related to vortices and their behaviors in particle systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GEBURTSDATUM
    -0.46
     ExecuteAsync
    -0.43
     EconPapers
    -0.40
    ReusableCell
    -0.36
    Демографія
    -0.36
    Geschiedenis
    -0.35
     Schild
    -0.35
    pannt
    -0.34
     Glaub
    -0.34
    ViewFeatures
    -0.34
    POSITIVE LOGITS
     vortex
    1.20
    Vortex
    1.08
     Vortex
    1.05
     vortices
    1.01
    vortex
    1.00
     whirlpool
    0.85
     tornado
    0.82
    Tornado
    0.82
     swirling
    0.80
     swirl
    0.78
    Activations Density 0.585%

    No Known Activations