© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 5264
    Prev
    Next
    INDEX
    Explanations

    prepositions indicating relationships or connections

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

    preposition followed by determiner

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    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
    MigrationBuilder
    -0.75
    хьтан
    -0.68
     otomatig
    -0.68
     BrowserModule
    -0.66
    ghijklmnop
    -0.65
    Predecesor
    -0.64
     صوتيه
    -0.64
    閖
    -0.63
     lizenzfreies
    -0.63
     queſta
    -0.63
    POSITIVE LOGITS
    s
    0.39
     gars
    0.38
     the
    0.33
    躇
    0.33
     Voici
    0.32
    Voici
    0.31
     ourselves
    0.31
     a
    0.31
     soit
    0.30
     something
    0.29
    Activations Density 0.008%

    No Known Activations