Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 7655
    Prev
    Next
    INDEX
    Explanations

    references to medical or anatomical terms related to "trachea"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lė
    -0.39
     veiks
    -0.32
     souci
    -0.32
     Bueno
    -0.32
    openzeppelin
    -0.31
     defaultstate
    -0.31
    ņem
    -0.30
    hirkan
    -0.30
     cuchara
    -0.30
    👔
    -0.29
    POSITIVE LOGITS
     Tra
    3.95
    Tra
    3.70
     tra
    3.66
    tra
    3.44
     TRA
    2.97
     тра
    2.81
     Тра
    2.78
    TRA
    2.48
     trac
    2.44
    トラ
    2.34
    Activations Density 0.108%

    No Known Activations