© 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. 1061
    Prev
    Next
    INDEX
    Explanations

    instances of the character apostrophe followed by various characters and terms, indicating possessiveness or contractions

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

    mathematical symbols or punctuation used in algebraic variable notation (like x', q'th term, etc.).

    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
    GOTREF
    -0.75
     فريبيس
    -0.72
     CommonModule
    -0.70
     defaultstate
    -0.62
    GeoNames
    -0.61
    ExtendWith
    -0.60
    findpost
    -0.59
     AssemblyCompany
    -0.56
     arşivlendi
    -0.56
    ContentAsync
    -0.56
    POSITIVE LOGITS
    s
    0.73
    \'
    0.55
    €™
    0.53
    prime
    0.52
    -'
    0.52
    |'
    0.52
    $'
    0.49
     ’
    0.46
     noastră
    0.46
     '
    0.45
    Activations Density 0.156%

    No Known Activations