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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 5755
    Prev
    Next
    INDEX
    Explanations

    references to musical instruments and cultural elements

    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
     ویکی‌پدی
    -0.64
    MemoryWarning
    -0.47
     Chwiliwch
    -0.47
     دیکھیے
    -0.45
    Referencies
    -0.45
    Diwedd
    -0.44
    ьажоргаш
    -0.43
    yarnpkg
    -0.42
    merksamkeit
    -0.41
     Cough
    -0.41
    POSITIVE LOGITS
     Component
    1.18
     Element
    1.17
     Region
    0.99
     Module
    0.98
    Component
    0.97
     Section
    0.96
     Feature
    0.96
     Unit
    0.96
     Segment
    0.90
     Layer
    0.89
    Activations Density 0.526%

    No Known Activations