© 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. 20-GEMMASCOPE-RES-65K
    11. 632
    Prev
    Next
    INDEX
    Explanations

    questions directed at the reader, particularly those involving personal experiences or inquiries

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

    phrases or questions that prompt introspection or self-reflection

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

    have you ever questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     offenbar
    -0.48
     trụ
    -0.48
     EconPapers
    -0.47
    assertSame
    -0.47
    uestamente
    -0.47
     beginnetje
    -0.46
    lnie
    -0.46
     entiendo
    -0.45
    InSection
    -0.45
    EndContext
    -0.45
    POSITIVE LOGITS
     ever
    1.09
    Ever
    0.86
    ever
    0.83
     Ever
    0.82
     wondered
    0.77
     EVER
    0.77
    wonder
    0.76
     wonder
    0.74
     noticed
    0.73
     notice
    0.71
    Activations Density 0.028%

    No Known Activations