© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 7948
    Prev
    Next
    INDEX
    Explanations

    biological and genetic terms related to viruses and their components

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

    medical terms related to diseases, genetic conditions, and scientific research.

    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
     Kebijakan
    -0.32
    遣
    -0.31
     generalizations
    -0.31
     speciality
    -0.30
     συνε
    -0.29
     combinations
    -0.29
     المت
    -0.29
     absoluto
    -0.29
     principal
    -0.28
     specialist
    -0.28
    POSITIVE LOGITS
    UnusedPrivate
    0.91
     المعيارى
    0.79
     ویکی‌پدی
    0.78
    abestanden
    0.75
    UrlResolution
    0.68
    Tikang
    0.67
     незавершена
    0.67
     NSCoder
    0.66
    хьтан
    0.65
    saraba
    0.64
    Activations Density 0.937%

    No Known Activations