© 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. 696
    Prev
    Next
    INDEX
    Explanations

    conjunctions and contrasting phrases in discussions regarding conditions or characteristics

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

    contrasting conjunctions indicating exceptions or limitations

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

    but rather

    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
    Переваги
    -0.53
    ionados
    -0.47
    AutoScale
    -0.47
     gradova
    -0.44
    Sans
    -0.44
    cdn
    -0.43
    eren
    -0.43
    lapsingToolbar
    -0.43
    fclose
    -0.43
    ScopeManager
    -0.42
    POSITIVE LOGITS
     vielmehr
    1.52
    而是
    1.32
     simply
    1.23
    むしろ
    1.22
     rather
    1.17
     merely
    1.11
     instead
    1.07
     Instead
    1.04
     anzi
    1.02
     Rather
    1.00
    Activations Density 0.087%

    No Known Activations