© 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. 1-GEMMASCOPE-RES-16K
    11. 7789
    Prev
    Next
    INDEX
    Explanations

    terms related to geographic or geographical concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CppCodeGen
    -0.72
    rancy
    -0.59
    nsito
    -0.53
    enido
    -0.53
     alcun
    -0.52
    原始内容存档于
    -0.52
    chinen
    -0.52
     stems
    -0.52
    ectady
    -0.52
     للمعارف
    -0.52
    POSITIVE LOGITS
     geographic
    2.02
     geographical
    2.00
     Geographic
    1.91
     Geographical
    1.86
    Geographic
    1.78
    Geographical
    1.59
     geography
    1.55
     geographically
    1.53
    geographic
    1.49
     Geography
    1.41
    Activations Density 0.233%

    No Known Activations