© 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. 5385
    Prev
    Next
    INDEX
    Explanations

    information related to health studies and their methodologies

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

    technical and medical research language about developing targeted therapies and understanding disease processes.

    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
     {},
    
    -0.61
    Становништво
    -0.61
     Bewußt
    -0.60
     Monfieur
    -0.59
    itinéraire
    -0.59
    Personendaten
    -0.59
    FlatList
    -0.57
    `,
    
    -0.56
     ModelExpression
    -0.55
     wireType
    -0.54
    POSITIVE LOGITS
    .
    0.56
    .\\
    0.56
    <eos>
    0.54
    .”
    0.52
    ."""
    0.50
    ."
    0.48
    。
    0.47
    .
    0.45
    '.
    0.45
    .}
    0.45
    Activations Density 1.004%

    No Known Activations