Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 19-GEMMASCOPE-RES-16K
    6. 2968
    Prev
    Next
    INDEX
    Explanations

    references to breast and lactation-related topics, particularly concerning health and medical conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     שוליים
    -0.74
    WebVitals
    -0.59
     Jop
    -0.54
     rangi
    -0.54
     pyrite
    -0.54
    BeginContext
    -0.53
     Mesopotamia
    -0.51
    Emin
    -0.51
    وفة
    -0.50
     cune
    -0.50
    POSITIVE LOGITS
     milk
    1.57
     breast
    1.39
     Milk
    1.35
    milk
    1.35
    Milk
    1.31
     Breast
    1.25
     MILK
    1.21
     lactation
    1.18
    breast
    1.17
    Breast
    1.16
    Activations Density 0.186%

    No Known Activations