© 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. 16-GEMMASCOPE-RES-16K
    11. 1961
    Prev
    Next
    INDEX
    Explanations

    references to specific locations and economic contexts, particularly in relation to Ghana

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

    Ghana and currencies

    np_acts-logits-general · gemini-2.0-flash

    Ghana

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ialah
    -0.44
    hindi
    -0.44
     Polskiego
    -0.43
    ̣n
    -0.43
     ال
    -0.42
    ₹
    -0.42
     Fawcett
    -0.41
     Neub
    -0.41
    aplic
    -0.41
    CRIPTION
    -0.41
    POSITIVE LOGITS
     Ghana
    1.09
    Ghana
    1.04
     Ghanaian
    0.95
     Accra
    0.94
     Ghanaians
    0.93
    ghana
    0.76
    ftagPool
    0.71
     GNA
    0.71
    contentLoaded
    0.69
     Ashanti
    0.68
    Activations Density 0.033%

    No Known Activations