© 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. 13604
    Prev
    Next
    INDEX
    Explanations

    medical and biological terms related to cancer, genetics, and diagnostic procedures

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

    medical and scientific terminology related to diseases, diagnostic techniques, and biological 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
    oa̍t
    -0.70
    Gambas
    -0.67
    tvguidetime
    -0.64
     يتيمه
    -0.58
     propOrder
    -0.57
    Халык
    -0.55
    出版年
    -0.54
    밌
    -0.54
    verwijspagina
    -0.54
    verifyException
    -0.54
    POSITIVE LOGITS
     adult
    0.40
    dbo
    0.40
     defStyleAttr
    0.39
     adults
    0.34
     Adult
    0.34
     male
    0.30
     Overland
    0.30
    RenderTarget
    0.30
     Mammal
    0.30
     daily
    0.30
    Activations Density 0.858%

    No Known Activations