© 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. 1-GEMMASCOPE-RES-16K
    11. 6811
    Prev
    Next
    INDEX
    Explanations

    terms related to the concept of "double" or "twice."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Berna
    -0.66
     للاسماء
    -0.63
     magnétique
    -0.61
     bursa
    -0.61
     démocratique
    -0.60
     judiciaire
    -0.60
     abstrait
    -0.59
     Mauritania
    -0.59
     Bernadette
    -0.58
     SqlConnection
    -0.58
    POSITIVE LOGITS
     double
    3.86
    double
    3.35
     Double
    3.34
    Double
    3.16
     DOUBLE
    3.13
     doubles
    2.96
    DOUBLE
    2.92
     triple
    2.89
     doble
    2.87
     doubled
    2.63
    Activations Density 0.084%

    No Known Activations