© 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. 22-GEMMASCOPE-RES-16K
    11. 12517
    Prev
    Next
    INDEX
    Explanations

    function definitions and their parameters in a codebase

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

    "instance" or "Instance"

    np_acts-logits-general · gemini-2.0-flash

    instance

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     ComVisible
    -0.58
    UMBIA
    -0.55
    теризу
    -0.54
    цездатний
    -0.54
    elung
    -0.52
    الإنجليزية
    -0.50
    astify
    -0.49
    ्रीय
    -0.48
    ̲
    -0.48
     LETTER
    -0.47
    POSITIVE LOGITS
     instance
    2.94
    instance
    2.81
    Instance
    2.50
     Instance
    2.45
     instances
    2.07
     INSTANCE
    2.03
    INSTANCE
    1.95
     instancia
    1.77
    实例
    1.75
     Instances
    1.68
    Activations Density 0.122%

    No Known Activations