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. 13888
    Prev
    Next
    INDEX
    Explanations

    phrases related to breast cancer and medical screening

    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
     genres
    -0.79
     regimes
    -0.71
     empires
    -0.71
    ต่างๆ
    -0.70
    setVerticalGroup
    -0.70
     formats
    -0.69
     governments
    -0.68
     departments
    -0.67
     Governments
    -0.66
     Formats
    -0.65
    POSITIVE LOGITS
     these
    0.68
     mga
    0.66
     those
    0.64
     THOSE
    0.61
     THESE
    0.61
     These
    0.61
    these
    0.58
    These
    0.58
     unos
    0.58
    those
    0.57
    Activations Density 0.639%

    No Known Activations