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. 37-GEMMASCOPE-RES-16K
    6. 3517
    Prev
    Next
    INDEX
    Explanations

    references to specific technical terms and concepts related to biology and computer science

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Tembelea
    -0.52
     eléctricas
    -0.49
     للمعارف
    -0.43
    لكتر
    -0.43
     elección
    -0.41
    исленность
    -0.41
     eléctrico
    -0.40
     etkili
    -0.38
     elástica
    -0.38
    جراء
    -0.38
    POSITIVE LOGITS
     dàng
    0.52
    ukone
    0.50
    setVerticalGroup
    0.48
    brite
    0.48
    OGND
    0.47
    twimg
    0.45
     szóci
    0.44
    FetchType
    0.43
     الرياضيه
    0.43
    <?
    0.43
    Activations Density 1.084%

    No Known Activations