© 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. 18-GEMMASCOPE-RES-16K
    11. 13832
    Prev
    Next
    INDEX
    Explanations

    references to specific geographical locations and their socio-economic contexts

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

    "Ghana" and related topics

    np_acts-logits-general · gemini-2.0-flash

    Ghana and Africa

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ₦
    -0.49
     hva
    -0.44
     barrera
    -0.40
     <=",
    -0.40
     tend
    -0.40
    θρω
    -0.39
     Unies
    -0.39
    Hindi
    -0.39
    hindi
    -0.39
     пунктов
    -0.39
    POSITIVE LOGITS
     Ghana
    1.16
    Ghana
    1.08
     Ghanaian
    1.04
     Ghanaians
    1.04
     Accra
    1.03
     useAppContext
    0.93
    ghana
    0.90
     Ashanti
    0.82
     Ghan
    0.81
     Sarko
    0.79
    Activations Density 0.011%

    No Known Activations