© 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-2-2B
    7. Residual Stream - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 3754
    Prev
    Next
    INDEX
    Explanations

    prepositions and phrases indicating direction or movement

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

    to locations or directions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     PTFE
    -0.57
     plupart
    -0.48
    لاث
    -0.45
    mayan
    -0.44
     perpétu
    -0.44
     nemlig
    -0.43
    一切
    -0.43
    を使用
    -0.43
    两种
    -0.43
    many
    -0.42
    POSITIVE LOGITS
     where
    1.04
    where
    0.83
    ViewFeatures
    0.66
     whence
    0.65
    wheres
    0.65
    hasMoreElements
    0.64
    dónde
    0.63
     donde
    0.61
     join
    0.60
     place
    0.60
    Activations Density 0.062%

    No Known Activations