© 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. 6699
    Prev
    Next
    INDEX
    Explanations

    phrases indicating duration or time periods

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

    phrases indicating a time duration, often using the word "for" followed by a time period.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    phrases that indicate durations or time spans, especially constructions specifying how long something lasted.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    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
     ostavi
    -0.43
     صفحۀ
    -0.40
     menik
    -0.38
    evos
    -0.37
    enciales
    -0.37
     nomb
    -0.36
    jár
    -0.35
     laude
    -0.35
     meil
    -0.35
     aprovecha
    -0.34
    POSITIVE LOGITS
     weeks
    0.62
     months
    0.57
     few
    0.54
     nearly
    0.54
    qtype
    0.54
     almost
    0.52
    weeks
    0.52
     pretty
    0.50
     years
    0.49
     several
    0.49
    Activations Density 0.217%

    No Known Activations