© 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. 38-GEMMASCOPE-RES-16K
    6. 7133
    Prev
    Next
    INDEX
    Explanations

    references to individuals with the initial "M" or related titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Rüyada
    -0.39
     ostavi
    -0.37
     stick
    -0.36
     double
    -0.34
     fast
    -0.34
     conf
    -0.34
     blast
    -0.32
     sticks
    -0.32
     עצ
    -0.32
     mr
    -0.32
    POSITIVE LOGITS
    PerformLayout
    0.49
     protoimpl
    0.46
    nextProps
    0.46
    UnitTesting
    0.45
     Italijanski
    0.45
     ویکی‌پدی
    0.44
    rillation
    0.44
     balanceOf
    0.44
    PMailer
    0.44
    lunch
    0.43
    Activations Density 0.377%

    No Known Activations