© 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. 20-GEMMASCOPE-RES-16K
    11. 5408
    Prev
    Next
    INDEX
    Explanations

    phrases indicating conditional relationships and dependencies

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

    Follows "of" or "the" in various contexts

    np_acts-logits-general · gemini-2.0-flash

    handling and description

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     flexibility
    -0.47
    sizeCache
    -0.46
     Difficulties
    -0.43
     convenience
    -0.42
     completa
    -0.42
     misterio
    -0.42
     comfortable
    -0.41
    ViewFeatures
    -0.41
    ecore
    -0.41
    IsMutable
    -0.41
    POSITIVE LOGITS
     dealings
    0.87
     handling
    0.85
     workmanship
    0.82
     approach
    0.78
     execution
    0.77
     wording
    0.77
     portrayal
    0.76
     disambiguazione
    0.76
    approach
    0.73
    对待
    0.72
    Activations Density 0.637%

    No Known Activations