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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 15170
    Prev
    Next
    INDEX
    Explanations

    references to breast cancer

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yarnpkg
    -0.73
    MessageOf
    -0.60
    /*---
    -0.58
    selig
    -0.55
    Constant
    -0.54
    jsii
    -0.54
    Nazionale
    -0.54
    CodeDom
    -0.52
     جغرافيا
    -0.51
     články
    -0.50
    POSITIVE LOGITS
     harvest
    0.86
     chest
    0.78
     breast
    0.77
     harvests
    0.74
     harvested
    0.72
    harvest
    0.71
     Chest
    0.70
    bewerken
    0.70
    bootstrap
    0.70
     Breast
    0.69
    Activations Density 0.075%

    No Known Activations