© 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. 28-GEMMASCOPE-RES-16K
    11. 11869
    Prev
    Next
    INDEX
    Explanations

    geographical locations and regions mentioned in the text

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

    Geographic regions (e.g., continents, seas)

    np_acts-logits-general · gemini-2.0-flash

    regions and countries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     global
    -0.39
     worldwide
    -0.35
     globally
    -0.35
     symbol
    -0.32
     meter
    -0.31
     possession
    -0.30
     thing
    -0.29
    廁
    -0.29
    AZIONE
    -0.29
     word
    -0.29
    POSITIVE LOGITS
     region
    1.01
    region
    0.97
     Region
    0.93
    Region
    0.88
     регионе
    0.83
     countries
    0.79
     REGION
    0.76
     région
    0.75
     regionales
    0.75
     Regional
    0.73
    Activations Density 0.366%

    No Known Activations