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

    Neuronpedia

    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. 20-GEMMASCOPE-RES-16K
    11. 913
    Prev
    Next
    INDEX
    Explanations

    references to influential individuals and their roles or achievements

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

    followed by "has," "have," or "'s"

    np_acts-logits-general · gemini-2.0-flash

    has or have

    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
    EDEFAULT
    -0.72
    Personendaten
    -0.62
    migrationBuilder
    -0.60
    /**
    -0.58
    Gön
    -0.55
    省市镇
    -0.54
    addContainerGap
    -0.54
     disambiguazione
    -0.53
    HtmlAttribute
    -0.53
     kaarangay
    -0.52
    POSITIVE LOGITS
     has
    2.28
     telah
    1.83
     have
    1.83
    has
    1.79
    Has
    1.71
     đã
    1.56
     Has
    1.55
     hath
    1.42
    have
    1.41
     Have
    1.41
    Activations Density 1.129%

    No Known Activations