© 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. 1523
    Prev
    Next
    INDEX
    Explanations

    the beginning of a new section or a significant change in topic

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

    the beginning of a document or text block

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

    gener ant completion

    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
     marching
    -0.58
     marched
    -0.55
    :].
    -0.54
     insuffisamment
    -0.52
    |}{}
    -0.52
    EndInit
    -0.52
     przypad
    -0.51
     useState
    -0.49
    TintMode
    -0.49
     marches
    -0.48
    POSITIVE LOGITS
    rungsseite
    0.74
    wikidata
    0.55
     елның
    0.54
     instead
    0.51
    而不是
    0.51
     anstatt
    0.50
     statt
    0.50
     avoid
    0.49
     stedet
    0.49
    instead
    0.48
    Activations Density 0.024%

    No Known Activations