© 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. 20-GEMMASCOPE-RES-16K
    11. 2558
    Prev
    Next
    INDEX
    Explanations

    references to legal documents, treaties, and political agreements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    historical dates, particularly those in the 1800s, and references to specific years.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     EconPapers
    -0.79
     AssemblyCulture
    -0.77
    
    -0.68
     prioritized
    -0.63
    brinco
    -0.62
    󠁣
    -0.62
    ViewFeatures
    -0.62
    AndEndTag
    -0.61
    findpost
    -0.61
     transformative
    -0.60
    POSITIVE LOGITS
     surla
    0.38
    ITURE
    0.27
     skall
    0.25
    tinyos
    0.24
    rile
    0.24
     perchè
    0.24
     głos
    0.24
     trä
    0.24
    ครับ
    0.24
    RegressionTest
    0.24
    Activations Density 0.152%

    No Known Activations