Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 4350
    Prev
    Next
    INDEX
    Explanations

    references to specific locations and cultural aspects related to Nepal

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

    Nepal and Nepali

    np_acts-logits-general · gemini-2.0-flash

    Nepal Kathmandu

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Spie
    -0.44
     Cie
    -0.44
    χι
    -0.43
     emu
    -0.43
    Emu
    -0.43
     genie
    -0.43
    joey
    -0.42
    ão
    -0.40
     dependencia
    -0.39
     brasili
    -0.39
    POSITIVE LOGITS
     Nepal
    1.10
     Nepali
    1.04
    Nepal
    0.97
     Kathmandu
    0.95
    LookAnd
    0.94
    mandu
    0.92
    KATH
    0.91
     nepal
    0.88
     Nep
    0.84
    RegressionTest
    0.83
    Activations Density 0.032%

    No Known Activations