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. 2608
    Prev
    Next
    INDEX
    Explanations

    terms related to mesenteric structures or functions, particularly in medical contexts

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

    Token "mes" or "Mes" followed by letters

    np_acts-logits-general · gemini-2.0-flash

    words starting with mes

    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
    ModelAdmin
    -0.61
    URIComponent
    -0.54
     parem
    -0.53
    kirakan
    -0.52
     complète
    -0.50
    qrstuvwxyz
    -0.50
     язык
    -0.50
    nodoc
    -0.50
    RefNanny
    -0.50
     каль
    -0.49
    POSITIVE LOGITS
     Mes
    1.03
    Mes
    0.96
     mes
    0.87
     MES
    0.84
    mybatisplus
    0.81
     Mess
    0.79
     MESS
    0.78
     незавершена
    0.75
    mes
    0.71
    Mess
    0.70
    Activations Density 0.082%

    No Known Activations