© 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. 897
    Prev
    Next
    INDEX
    Explanations

    temporal references and durations

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

    references to time periods, specifically years and durations (e.g., "years later", "10 years", specific years like 1924).

    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
    Personensuche
    -0.66
     متعلقه
    -0.64
     dieſe
    -0.64
     zelve
    -0.63
    protoimpl
    -0.63
     zijne
    -0.63
     للمعارف
    -0.61
     ModelExpression
    -0.61
    出版年
    -0.59
    afficheront
    -0.59
    POSITIVE LOGITS
    EndContext
    0.60
     years
    0.43
     decades
    0.41
     decade
    0.40
     Years
    0.38
     broken
    0.33
    years
    0.33
     consum
    0.32
    VersionUID
    0.32
    Years
    0.32
    Activations Density 0.110%

    No Known Activations