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. 2602
    Prev
    Next
    INDEX
    Explanations

    references to solar activity and its effects on Earth

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

    Solar activity and plasma

    np_acts-logits-general · gemini-2.0-flash

    solar phenomena, plasma, coronal

    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
    ScopeManager
    -0.55
     Beckett
    -0.53
    asker
    -0.53
     المعيارى
    -0.50
    imageshack
    -0.50
     nhiêu
    -0.49
     незавершена
    -0.48
    kään
    -0.46
     Sanger
    -0.45
    Housing
    -0.45
    POSITIVE LOGITS
     plasma
    0.92
     Plasma
    0.84
    Plasma
    0.78
    plasma
    0.77
     solar
    0.74
     Solar
    0.73
    Solar
    0.70
     coronal
    0.69
     solare
    0.67
     ion
    0.66
    Activations Density 0.508%

    No Known Activations