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-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 5518
    Prev
    Next
    INDEX
    Explanations

    aspects related to aerodynamic data and its sources

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

    "Aerodynamic" or "airfoil" terms

    np_acts-logits-general · gemini-2.0-flash

    aerodynamic airfoil data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
     سكانية
    -0.63
     ratchet
    -0.58
     cerebellar
    -0.57
     macular
    -0.54
    Scaffold
    -0.54
    Демографія
    -0.53
     Scaffold
    -0.53
    ocere
    -0.52
     cistern
    -0.52
    CppMethod
    -0.52
    POSITIVE LOGITS
     aerodynamic
    1.01
     aer
    0.82
     aéro
    0.78
     wind
    0.75
     drag
    0.74
     Aer
    0.72
    Aer
    0.70
     airfoil
    0.69
    aer
    0.66
     spoilers
    0.64
    Activations Density 0.320%

    No Known Activations