© 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. 4657
    Prev
    Next
    INDEX
    Explanations

    specific medical terminology and concepts related to health and diseases

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

    medical terminology and abbreviations, particularly in research and academic medical contexts.

    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
     kaynağından
    -0.52
    "}}
    -0.48
    '}}
    -0.45
    Tembelea
    -0.44
     ProtoMessage
    -0.44
    رشف
    -0.43
    "}}>
    -0.43
    outWeight
    -0.42
    `{.
    -0.42
    ⒍
    -0.41
    POSITIVE LOGITS
    FormTagHelper
    0.46
    chooser
    0.42
     deſt
    0.41
    InjectAttribute
    0.39
     ſen
    0.38
     whoſe
    0.38
    ActionMode
    0.36
    ēm
    0.36
     mergeFrom
    0.36
     communautés
    0.35
    Activations Density 0.266%

    No Known Activations