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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 19-GEMMASCOPE-RES-16K
    11. 3364
    Prev
    Next
    INDEX
    Explanations

    topics related to covering and protecting privacy, particularly concerning children and sensitive situations

    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
    WebVitals
    -0.76
    Tracce
    -0.66
    tagHelper
    -0.62
    bootstrapcdn
    -0.61
    SPATH
    -0.59
    ContentLoaded
    -0.58
    Чыганаклар
    -0.55
     pingente
    -0.54
    DIPSETTING
    -0.54
    jenih
    -0.54
    POSITIVE LOGITS
     cover
    1.69
     covers
    1.56
     covered
    1.54
    Cover
    1.54
     covering
    1.51
     Cover
    1.50
     Covering
    1.50
    cover
    1.45
     COVER
    1.42
     Covers
    1.41
    Activations Density 0.369%

    No Known Activations