© 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. 38-GEMMASCOPE-RES-16K
    11. 7605
    Prev
    Next
    INDEX
    Explanations

    references to companies and certifications related to health and energy efficiency

    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
     Vorstellungen
    -0.45
     Einf
    -0.34
    disposing
    -0.32
     planea
    -0.32
    NegativeButton
    -0.31
     innamor
    -0.31
     Überras
    -0.31
    地说道
    -0.31
    เด
    -0.31
    Budget
    -0.30
    POSITIVE LOGITS
     certification
    2.11
     certified
    1.93
     certifying
    1.82
     certify
    1.80
     Certification
    1.79
     certifications
    1.77
    certification
    1.77
    certified
    1.73
    Certification
    1.66
     certific
    1.65
    Activations Density 0.325%

    No Known Activations