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-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 364
    Prev
    Next
    INDEX
    Explanations

    terms related to mathematical and scientific modeling of efficiency and rates in systems

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

    mathematical and scientific notation, particularly related to physics equations and technical parameters.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 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
    ANDED
    -0.42
     Wier
    -0.41
     wob
    -0.41
     Kraw
    -0.40
     Cereal
    -0.39
     Fro
    -0.39
    hamilan
    -0.39
     flung
    -0.38
    jà
    -0.38
     Funk
    -0.38
    POSITIVE LOGITS
     rate
    0.76
    rate
    0.67
    Rate
    0.66
     Rate
    0.65
     rates
    0.62
    SourceChecksum
    0.62
     speeds
    0.61
    存于互联网档案馆
    0.61
    Datuak
    0.60
    Rates
    0.60
    Activations Density 0.719%

    No Known Activations