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. 21-GEMMASCOPE-RES-16K
    6. 7565
    Prev
    Next
    INDEX
    Explanations

    content related to Nepalese culture and identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    χι
    -0.45
    Emu
    -0.42
    vių
    -0.41
    答案
    -0.40
     answers
    -0.39
    joey
    -0.39
    ão
    -0.39
     answer
    -0.39
     Cie
    -0.38
    الع
    -0.38
    POSITIVE LOGITS
     Nepal
    1.15
     Nepali
    1.07
     Kathmandu
    1.04
    LookAnd
    1.01
    Nepal
    1.00
    mandu
    0.92
     nepal
    0.91
    KATH
    0.91
    RegressionTest
    0.89
     Nep
    0.86
    Activations Density 0.024%

    No Known Activations