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. 4789
    Prev
    Next
    INDEX
    Explanations

    key terms and concepts related to parasitic infections and their effects on health

    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
     NSCoder
    -0.66
    SharedDtor
    -0.59
    idopsis
    -0.58
     Albe
    -0.53
     knuckles
    -0.53
     subtilis
    -0.53
     justiça
    -0.53
     Phoen
    -0.52
     fotografico
    -0.49
     Rockford
    -0.49
    POSITIVE LOGITS
     Paras
    1.23
     parasite
    1.20
     parasites
    1.19
     paras
    1.14
    Paras
    1.12
     parasitic
    1.10
    paras
    1.08
     worm
    0.91
    asitic
    0.88
     worms
    0.86
    Activations Density 0.810%

    No Known Activations