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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 6476
    Prev
    Next
    INDEX
    Explanations

    terms related to fluid dynamics and physical properties of materials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    wieś
    -0.57
    WebMethod
    -0.56
    unitOfWork
    -0.55
     getItemCount
    -0.53
     actionPerformed
    -0.50
     contento
    -0.50
    Felic
    -0.50
    gewicht
    -0.49
    SEGUIR
    -0.47
    UIControlState
    -0.46
    POSITIVE LOGITS
     Reynolds
    0.91
    Reynolds
    0.79
     Reyn
    0.73
     flow
    0.68
    流
    0.68
     AspNetCore
    0.68
    Reyn
    0.67
     stream
    0.66
     consultato
    0.64
     viscosity
    0.64
    Activations Density 0.766%

    No Known Activations