© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 0-GEMMASCOPE-RES-65K
    11. 10046
    Prev
    Next
    INDEX
    Explanations

    varying forms of the word "cover"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    XmlType
    -0.66
    íncia
    -0.57
     tabPage
    -0.55
    izability
    -0.54
     jambes
    -0.52
    CPtr
    -0.50
    imbangan
    -0.49
    gog
    -0.49
    Repeating
    -0.49
     pasteles
    -0.49
    POSITIVE LOGITS
    cover
    1.56
    Cover
    1.52
     cover
    1.52
     Cover
    1.46
    COVER
    1.41
     Covers
    1.32
    Covers
    1.27
     covers
    1.26
     COVER
    1.24
    covers
    1.23
    Activations Density 0.104%

    No Known Activations