© 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. 14-GEMMASCOPE-RES-16K
    11. 7480
    Prev
    Next
    INDEX
    Explanations

    names of locations, particularly cities and towns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enumi
    -0.69
    calaure
    -0.60
    ISLAM
    -0.59
    identiality
    -0.57
    annen
    -0.56
    skosten
    -0.56
     Pyrene
    -0.55
     BorderSide
    -0.55
    WWF
    -0.54
    domada
    -0.54
    POSITIVE LOGITS
     city
    0.92
     City
    0.81
     città
    0.80
    city
    0.76
     CITY
    0.73
    City
    0.71
     cities
    0.71
     cidade
    0.69
     ciudad
    0.69
     miasta
    0.67
    Activations Density 0.260%

    No Known Activations