© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 3421
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "have" and its various forms in the context of obligation or necessity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/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.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SourceChecksum
    -0.99
     resourceCulture
    -0.91
     الرياضيه
    -0.85
    verwijspagina
    -0.82
    AndEndTag
    -0.81
     Normdatei
    -0.77
     nahilalakip
    -0.75
    จึง
    -0.74
     kaarangay
    -0.73
     pauvreté
    -0.72
    POSITIVE LOGITS
    abo
    0.67
    文章
    0.61
    vener
    0.61
    have
    0.61
    × 
    0.59
    Holo
    0.59
     earlier
    0.59
    earlier
    0.57
     früher
    0.57
    abilirsiniz
    0.56
    Activations Density 0.102%

    No Known Activations