© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 9312
    Prev
    Next
    INDEX
    Explanations

    references to specific programming frameworks and libraries

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

    Comes before a Java method or class name

    np_acts-logits-general · gemini-2.0-flash

    Java persistence and EJB

    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
     professionali
    -0.63
    ollectionView
    -0.60
     Lesotho
    -0.59
     Ilya
    -0.58
    thodon
    -0.58
     Castello
    -0.57
     mohair
    -0.57
     ویکی‌پدیای
    -0.56
     estekak
    -0.56
    MLLoader
    -0.56
    POSITIVE LOGITS
     EntityManager
    0.71
    EntityManager
    0.62
     Bay
    0.56
     bay
    0.56
     Zub
    0.55
    getResultList
    0.53
     javax
    0.52
    classID
    0.52
     Walsh
    0.49
    ejb
    0.49
    Activations Density 0.173%

    No Known Activations