© 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. 16-GEMMASCOPE-RES-16K
    11. 8478
    Prev
    Next
    INDEX
    Explanations

    the concept of "double" or "twice" in various contexts

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

    "double" or plural variations

    np_acts-logits-general · gemini-2.0-flash

    double [word]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Datuak
    -0.90
     initComponents
    -0.87
     متعلقه
    -0.71
    脚注の使い方
    -0.68
    IsContent
    -0.65
     préfé
    -0.62
    :&
    -0.58
    Person
    -0.57
     whereof
    -0.57
    şen
    -0.57
    POSITIVE LOGITS
     DOUBLE
    1.16
     Double
    1.15
     doubles
    1.15
     double
    1.15
     Doubles
    1.14
    DOUBLE
    1.10
    Double
    1.10
    Doubles
    1.09
    double
    1.06
    doubles
    1.04
    Activations Density 0.127%

    No Known Activations