© 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. 5944
    Prev
    Next
    INDEX
    Explanations

    formatted numerical data, particularly related to measurements and conversions

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

    Numbers with periods as separators

    np_acts-logits-general · gemini-2.0-flash

    numbers and measurements

    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
    1
    -0.58
    3
    -0.55
    5
    -0.54
    7
    -0.54
     
    -0.54
    2
    -0.52
    4
    -0.50
    6
    -0.49
    diga
    -0.48
    ran
    -0.48
    POSITIVE LOGITS
     propOrder
    1.28
    Geplaatst
    1.22
    ьаж
    1.15
     EClass
    1.15
     ویکی‌پدیا
    1.14
     EconPapers
    1.12
    تقاوى
    1.09
    featureID
    1.09
     Roskov
    1.08
     kaarangay
    1.06
    Activations Density 0.631%

    No Known Activations