© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 15286
    Prev
    Next
    INDEX
    Explanations

    specialized legal and formal references in documents

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

    Numbers following specific terms

    np_acts-logits-general · gemini-2.0-flash

    numbers after "number"

    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
    GEBURTSDATUM
    -0.79
    PerformLayout
    -0.73
    tagHelperRunner
    -0.72
    WaitGroup
    -0.69
    ως
    -0.68
     Akismet
    -0.64
     religieuses
    -0.62
     ویکی
    -0.61
     الاطلاع
    -0.60
    الإنجليزية
    -0.59
    POSITIVE LOGITS
    ContentLoaded
    0.57
    PageIndex
    0.55
    AFFIRMED
    0.52
    $\#
    0.50
    akhstan
    0.49
    <bos>
    0.49
     Audiodateien
    0.49
    phoria
    0.49
    cendental
    0.48
    __).
    0.47
    Activations Density 0.734%

    No Known Activations