© 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. 9948
    Prev
    Next
    INDEX
    Explanations

    numerical data related to medical assessments, particularly focused on patient characteristics and treatment outcomes

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

    medical and scientific research terminology related to cancer, cells, and experimental methods.

    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
     Chwiliwch
    -0.69
     Administrativna
    -0.68
    Personendaten
    -0.66
    RenderAtEndOf
    -0.65
    GTCX
    -0.62
     мәкал
    -0.60
    twimg
    -0.59
    
    -0.57
     AssemblyCulture
    -0.57
    getMenuInflater
    -0.55
    POSITIVE LOGITS
    genossen
    0.38
    old
    0.38
    9
    0.37
    ItemID
    0.36
    শে
    0.36
    6
    0.35
    5
    0.34
    glory
    0.33
    Thomas
    0.33
    8
    0.33
    Activations Density 1.649%

    No Known Activations