© 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 - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 13093
    Prev
    Next
    INDEX
    Explanations

    geographical and community-related terms, particularly those that denote specific locations or administrative areas

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     aces
    -0.46
     perception
    -0.45
    cass
    -0.44
    cach
    -0.44
    collo
    -0.44
    Campaign
    -0.44
    initas
    -0.44
     Gin
    -0.44
     carto
    -0.43
     elective
    -0.43
    POSITIVE LOGITS
    TagMode
    0.54
    principalTable
    0.52
    ьаж
    0.51
     &___
    0.50
     kasarigan
    0.48
    AppMethodBeat
    0.47
     disambiguazione
    0.41
     OFDb
    0.40
    setVerticalGroup
    0.39
     autorytatywna
    0.39
    Activations Density 0.825%

    No Known Activations