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. 14239
    Prev
    Next
    INDEX
    Explanations

    references to "mycobacterium" and variations of the word "my"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    InjectAttribute
    -0.67
     saites
    -0.64
     menge
    -0.50
     minimally
    -0.50
     remercier
    -0.50
    ঁ
    -0.49
     وسلم
    -0.49
    talt
    -0.49
     cancelación
    -0.48
     tearDown
    -0.48
    POSITIVE LOGITS
    sterious
    0.76
     My
    0.73
     own
    0.71
    riad
    0.65
     MY
    0.64
    getMy
    0.62
    My
    0.61
     Mijn
    0.61
    embro
    0.61
     Catawiki
    0.61
    Activations Density 0.075%

    No Known Activations