© 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. 22-GEMMASCOPE-RES-16K
    6. 7102
    Prev
    Next
    INDEX
    Explanations

    import statements and component definitions in React code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     '\\;'
    -0.60
    UnusedPrivate
    -0.56
    脚注の使い方
    -0.53
     Katzen
    -0.51
     StatelessWidget
    -0.50
    CloseOperation
    -0.49
    PostExecute
    -0.49
    StoreMessageInfo
    -0.48
    CppCodeGen
    -0.48
    rawDesc
    -0.47
    POSITIVE LOGITS
    المناصب
    0.58
    клопе
    0.55
     Aff
    0.54
    السكان
    0.54
     Segment
    0.53
     חיצוניים
    0.53
     cherchés
    0.53
    تقاوى
    0.52
    Seg
    0.50
    اصله
    0.50
    Activations Density 0.076%

    No Known Activations