© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 12702
    Prev
    Next
    INDEX
    Explanations

    terminology related to inflammation and its associated biomarkers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Demografía
    -0.58
    outWeight
    -0.56
     nahilalakip
    -0.54
    HomeAsUpEnabled
    -0.54
     سكانية
    -0.49
    LookAnd
    -0.49
    SharedCtor
    -0.48
    ///</
    -0.46
    المناصب
    -0.46
    PropertyChanging
    -0.45
    POSITIVE LOGITS
     inflammation
    1.15
     Inflammation
    1.13
    inflammation
    1.13
     inflammatory
    1.08
    lammatory
    1.03
    inflammatory
    1.02
    mmation
    0.97
     Inflammatory
    0.97
    Infla
    0.91
     infla
    0.87
    Activations Density 0.576%

    No Known Activations