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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 6781
    Prev
    Next
    INDEX
    Explanations

    references to British entities and geographical locations

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

    Refers to locations in the UK

    np_acts-logits-general · gemini-2.0-flash

    UK, Britain, England

    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
     Dubuque
    -0.72
    万美元
    -0.69
     econô
    -0.61
    inigte
    -0.58
     Marietta
    -0.57
    Honolulu
    -0.57
     Winona
    -0.56
     Folsom
    -0.56
     Girard
    -0.55
     BytesLike
    -0.55
    POSITIVE LOGITS
     British
    1.74
    British
    1.60
     UK
    1.59
     Britain
    1.58
     England
    1.57
     Britons
    1.52
     London
    1.50
    Britain
    1.45
     BRITISH
    1.44
     british
    1.44
    Activations Density 1.229%

    No Known Activations