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. 18-GEMMASCOPE-RES-16K
    6. 1466
    Prev
    Next
    INDEX
    Explanations

    locations and events related to public gatherings and protests

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

    Locations or mentions of Bangladesh

    np_acts-logits-general · gemini-2.0-flash

    Bangladesh places and dates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atche
    -0.61
    ANNES
    -0.60
     NSCoder
    -0.60
     الرياضيه
    -0.59
    istoitu
    -0.58
    Autoritní
    -0.57
    ConverterFactory
    -0.54
    rrggbb
    -0.54
     poveznice
    -0.53
    ViewById
    -0.53
    POSITIVE LOGITS
     Bangladesh
    1.00
    Bangladesh
    0.89
     Dhaka
    0.82
     Banglades
    0.79
     Chowdhury
    0.77
     Bang
    0.66
    Bang
    0.66
    AndEndTag
    0.64
     Sonar
    0.62
     Bengali
    0.61
    Activations Density 0.058%

    No Known Activations