© 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 - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 5308
    Prev
    Next
    INDEX
    Explanations

    instances of the word "When" and its surrounding context, indicating a focus on questions or statements about timing and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tangentMode
    -0.76
    MLLoader
    -0.73
    NameInMap
    -0.69
     čia
    -0.68
     AppDelegate
    -0.65
     EconPapers
    -0.62
     تضيفلها
    -0.61
     JpaRepository
    -0.60
    曖昧さ回避
    -0.60
     propOrder
    -0.58
    POSITIVE LOGITS
     WHEN
    0.97
     When
    0.95
     when
    0.93
    When
    0.92
    when
    0.91
    WHEN
    0.87
    Cuando
    0.82
    cuando
    0.80
     cuando
    0.80
     Cuando
    0.74
    Activations Density 0.199%

    No Known Activations