© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 11497
    Prev
    Next
    INDEX
    Explanations

    names of locations and streets, particularly in Liverpool

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Liverpool and other related locations

    np_acts-logits-general · gemini-2.0-flash

    Liverpool institutions and events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     initComponents
    -0.78
     Boulder
    -0.65
     Lesotho
    -0.64
    Boulder
    -0.63
     MASSACHUSETTS
    -0.61
     COLORADO
    -0.61
     Laramie
    -0.61
     Colorado
    -0.61
    msford
    -0.60
    Colorado
    -0.59
    POSITIVE LOGITS
     Liverpool
    1.41
    Liverpool
    1.26
     Merseyside
    1.14
     LIVER
    1.06
     Mersey
    1.02
     Anfield
    1.00
     liverpool
    0.98
     Liver
    0.91
     Klopp
    0.91
     Beatles
    0.82
    Activations Density 0.125%

    No Known Activations