© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 105012
    Prev
    Next
    INDEX
    Explanations

    beginning or structure indicators in a text

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    The token "bos" appearing between triple angle brackets, representing the beginning of a sequence marker in a dataset.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219
    Triggered by @lu-christina
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    Negative Logits
    sizeCache
    -0.96
    httphttps
    -0.83
    Personendaten
    -0.76
    WebElementEntity
    -0.73
    addCriterion
    -0.71
    Erreferentziak
    -0.70
    تقاوى
    -0.70
     jspb
    -0.67
     nakalista
    -0.67
    webElementXpaths
    -0.67
    POSITIVE LOGITS
     res
    0.34
     order
    0.34
     outside
    0.34
     Weing
    0.34
     Ant
    0.34
     spite
    0.33
     det
    0.32
     also
    0.32
     Williams
    0.32
     sto
    0.32
    Activations Density 0.091%

    No Known Activations