© 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. 7627
    Prev
    Next
    INDEX
    Explanations

    scientific terminology related to research gaps and empirical analysis

    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
     ویکی‌پدیای
    -0.41
    はじめに
    -0.36
     reciente
    -0.36
     traditionnel
    -0.36
    想到
    -0.35
     AssemblyCompany
    -0.35
    下载附件
    -0.35
    Traditional
    -0.35
    latest
    -0.34
    famous
    -0.34
    POSITIVE LOGITS
     quantitative
    0.83
     improved
    0.74
    quantitative
    0.68
     unified
    0.68
    AndEndTag
    0.68
    improved
    0.67
     novel
    0.67
     comprehensive
    0.64
     Quantitative
    0.63
     systematic
    0.62
    Activations Density 1.676%

    No Known Activations