© 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. 18-GEMMASCOPE-RES-16K
    11. 513
    Prev
    Next
    INDEX
    Explanations

    numerical values and financial data

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

    Numbers followed by a unit of measurement

    np_acts-logits-general · gemini-2.0-flash

    numbers followed by units or specific terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    parsedMessage
    -0.91
    webElementXpaths
    -0.74
    IsMutable
    -0.74
    richTextPanel
    -0.73
    RegressionTest
    -0.67
     EconPapers
    -0.65
    AsUp
    -0.65
    ViewFeatures
    -0.62
    ThroughAttribute
    -0.61
    ":[{
    -0.61
    POSITIVE LOGITS
    ValueStyle
    0.79
     Audiodateien
    0.65
    estris
    0.53
    ècie
    0.52
    học
    0.50
     WPS
    0.49
    piele
    0.48
    buie
    0.47
    pegno
    0.47
    ließ
    0.47
    Activations Density 0.625%

    No Known Activations