© 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. 28-GEMMASCOPE-RES-16K
    11. 3590
    Prev
    Next
    INDEX
    Explanations

    details related to patient demographics and clinical characteristics

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

    a patient or patients

    np_acts-logits-general · gemini-2.0-flash

    patient medical conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AddTagHelper
    -0.47
    AndroidJUnit
    -0.46
    ſelf
    -0.45
    djangoproject
    -0.44
    ביוגרפיה
    -0.43
    httphttps
    -0.42
    </thead>
    -0.42
    Transkript
    -0.41
     Itself
    -0.40
     itself
    -0.40
    POSITIVE LOGITS
     suffering
    0.73
     دچار
    0.65
     suffer
    0.65
     suffers
    0.65
    suffering
    0.61
     sufre
    0.60
     underwent
    0.59
     undergoing
    0.57
     sufrir
    0.54
     Suffering
    0.54
    Activations Density 1.382%

    No Known Activations