© 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. 16-GEMMASCOPE-RES-16K
    11. 14648
    Prev
    Next
    INDEX
    Explanations

    references to Malaysian and Malay culture, particularly in relation to cuisine and ethnicity

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

    Malaysia, Asian countries, or Malay language

    np_acts-logits-general · gemini-2.0-flash

    Malaysia Asian tropical jungle

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Obrázky
    -0.78
    #
    -0.72
    detectChanges
    -0.68
     ewes
    -0.67
    (&:
    -0.63
     formaggio
    -0.63
    θος
    -0.62
     Jagger
    -0.62
     Ips
    -0.61
     Lampard
    -0.58
    POSITIVE LOGITS
     tropical
    1.04
     tropics
    0.98
     Tropical
    0.94
     Malay
    0.92
     jungle
    0.91
     tropicales
    0.89
    Malaysia
    0.87
     Malaysia
    0.86
     coconut
    0.86
    Malay
    0.84
    Activations Density 0.326%

    No Known Activations