© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 12349
    Prev
    Next
    INDEX
    Explanations

    medical terminology related to diagnosis and symptoms

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

    medical terminology and detailed descriptions of health conditions.

    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
     للاسماء
    -0.94
     AssemblyCulture
    -0.88
    GEBURTSDATUM
    -0.86
    Gweler
    -0.78
    Geplaatst
    -0.77
    adaptiveStyles
    -0.76
    ſchaft
    -0.75
     nakalista
    -0.75
    󠁢
    -0.74
    
    -0.74
    POSITIVE LOGITS
     privilégi
    0.24
     NH
    0.24
     Specifically
    0.24
     utwor
    0.23
    protoimpl
    0.22
    losigkeit
    0.22
    envolvimento
    0.21
    Th
    0.21
    zahl
    0.21
    NSS
    0.21
    Activations Density 0.020%

    No Known Activations