Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 1547
    Prev
    Next
    INDEX
    Explanations

    references to successful authors and the series they produce

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

    Followed by "series," "book," or "taxa."

    np_acts-logits-general · gemini-2.0-flash

    detecting continuation of series

    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
     فريبيس
    -0.59
    seiti
    -0.54
    addWidget
    -0.50
    agramm
    -0.49
    ISupport
    -0.47
    UnitTesting
    -0.47
    Autowired
    -0.45
    WidgetItem
    -0.43
    addTab
    -0.42
    rscheinlichkeit
    -0.42
    POSITIVE LOGITS
     series
    3.03
    series
    2.65
     Series
    2.34
     SERIES
    2.28
    Series
    2.24
     serie
    2.15
     série
    2.15
    SERIES
    2.02
    系列
    1.99
    シリーズ
    1.95
    Activations Density 0.380%

    No Known Activations