© 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. 101054
    Prev
    Next
    INDEX
    Explanations

    phrases related to reviews and recommendations

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

    The token sequence "of" appears in contexts where it typically follows the phrase "Read our full review" and precedes the name of a restaurant, dish, food service, or dining location, acting as a connector between the review mention and the subject being reviewed.

    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
    Vidite
    -0.64
     protoimpl
    -0.63
    featureID
    -0.61
    parsedMessage
    -0.59
    تقاوى
    -0.59
     Italijani
    -0.55
    windowFixed
    -0.55
    webElementXpaths
    -0.55
    WebElementEntity
    -0.55
    
    -0.54
    POSITIVE LOGITS
     
    0.35
    MouseAdapter
    0.35
     Sélection
    0.34
    󠁢
    0.34
     assurent
    0.33
    lète
    0.33
     Bos
    0.31
     Sho
    0.31
     nahilalakip
    0.31
    .*")]
    0.31
    Activations Density 0.008%

    No Known Activations