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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 11352
    Prev
    Next
    INDEX
    Explanations

    numerical data related to statistics or performance metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    انتهای
    -0.37
    élément
    -0.36
     considered
    -0.35
    velmente
    -0.34
     considerada
    -0.34
     Guggenheim
    -0.34
     awfully
    -0.33
    媲
    -0.33
     olvidado
    -0.33
     manufacturer
    -0.33
    POSITIVE LOGITS
     initComponents
    0.85
    WaitGroup
    0.72
    المشاركات
    0.63
    BufferException
    0.62
     CallOverrides
    0.61
    BagLayout
    0.58
    HomeAsUpEnabled
    0.58
    complexContent
    0.58
    InputBorder
    0.56
    AsUp
    0.56
    Activations Density 0.676%

    No Known Activations