© 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. 4492
    Prev
    Next
    INDEX
    Explanations

    phrases related to the inclusion or incorporation of elements

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

    following "include" or "inclusion"

    np_acts-logits-general · gemini-2.0-flash

    inclusion, included, includes

    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
    RegressionTest
    -0.92
     initComponents
    -0.90
     ***/
    -0.74
     يتيمه
    -0.72
    LookAnd
    -0.70
     Tavares
    -0.67
     الرياضيه
    -0.67
    WindowConstants
    -0.66
     jScrollPane
    -0.66
     مشين
    -0.66
    POSITIVE LOGITS
     INCLUDE
    1.02
     Include
    0.99
     Included
    0.90
    Includes
    0.90
     inclusions
    0.89
     included
    0.88
     Includes
    0.87
    includes
    0.87
    INCLUDED
    0.85
     includes
    0.84
    Activations Density 0.160%

    No Known Activations