© 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. 14-GEMMASCOPE-RES-16K
    6. 9332
    Prev
    Next
    INDEX
    Explanations

    terms related to medical and biological conditions, particularly focused on International Classification of Diseases (ICD) codes or classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ness
    -0.58
    škas
    -0.57
    ṅ
    -0.52
    çons
    -0.50
     metų
    -0.50
     žaid
    -0.47
    nya
    -0.47
    kapnya
    -0.47
    ụng
    -0.47
    OGRAPH
    -0.45
    POSITIVE LOGITS
    SSI
    0.87
    iri
    0.81
    SDI
    0.81
     Schi
    0.80
    STI
    0.80
    i
    0.80
    ini
    0.79
    Andi
    0.79
    ivi
    0.79
    Miri
    0.79
    Activations Density 0.552%

    No Known Activations