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. 16-GEMMASCOPE-RES-16K
    6. 12586
    Prev
    Next
    INDEX
    Explanations

    scientific terms and concepts related to atmospheric physics and celestial mechanics

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

    planetary radius or orbits

    np_acts-logits-general · gemini-2.0-flash

    lunar eclipse

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ValueStyle
    -0.59
     пожа
    -0.50
    DIL
    -0.48
    sizeCache
    -0.47
     مشين
    -0.45
    花板
    -0.44
    ooga
    -0.43
    arbox
    -0.43
     spea
    -0.42
     Pash
    -0.42
    POSITIVE LOGITS
     découver
    0.73
     orbits
    0.62
    ConverterFactory
    0.62
    
    0.61
     orbiting
    0.61
     محفوظة
    0.60
    ătoare
    0.60
     médicaux
    0.60
    يكب
    0.58
     enfans
    0.57
    Activations Density 0.341%

    No Known Activations