© 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. 22-GEMMASCOPE-RES-16K
    11. 2616
    Prev
    Next
    INDEX
    Explanations

    references to "cover" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "cover" (and variations)

    np_acts-logits-general · gemini-2.0-flash

    cover together with story or crops

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Voulez
    -0.63
     Dumont
    -0.59
     кӀ
    -0.59
     whereof
    -0.59
     linden
    -0.59
    וויק
    -0.59
    chaun
    -0.56
    Havolalar
    -0.56
    XtraReports
    -0.55
    glieder
    -0.54
    POSITIVE LOGITS
    tly
    1.17
    Covers
    0.86
    COVER
    0.85
     Covers
    0.83
     covers
    0.81
     COVER
    0.79
     ujednoznacz
    0.78
     Cover
    0.74
    Cover
    0.71
    cover
    0.69
    Activations Density 0.080%

    No Known Activations