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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 3759
    Prev
    Next
    INDEX
    Explanations

    references to Indian cuisine and dishes

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

    Referring to India or Indian culture

    np_acts-logits-general · gemini-2.0-flash

    Indian subcontinent

    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
    SpringBootTest
    -0.60
    ABL
    -0.45
    Enlaces
    -0.44
    iseta
    -0.44
     Þ
    -0.44
    ysql
    -0.43
    kiy
    -0.43
     ANGELES
    -0.41
    renz
    -0.41
     Miche
    -0.41
    POSITIVE LOGITS
     India
    1.22
     Indian
    1.21
     Indians
    1.20
     Hindus
    1.16
    Indian
    1.15
    India
    1.14
    Indians
    1.14
     Indien
    1.10
     INDIAN
    1.06
     indian
    1.06
    Activations Density 0.187%

    No Known Activations