© 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. 3-GEMMASCOPE-RES-16K
    11. 15801
    Prev
    Next
    INDEX
    Explanations

    structured data elements, particularly JSON-like syntax and attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ViewImports
    -0.95
    AndEndTag
    -0.95
    ImageContext
    -0.90
     mergeFrom
    -0.88
    didSet
    -0.84
    исленность
    -0.83
    ConstraintMaker
    -0.81
     AssemblyTitle
    -0.81
     consultato
    -0.80
     Meksiku
    -0.79
    POSITIVE LOGITS
    しま
    0.47
     parem
    0.46
     cụ
    0.45
    ंदीखरीदारी
    0.45
    այ
    0.44
     poj
    0.44
    {"
    0.44
    abord
    0.44
    яз
    0.43
    HasAnnotation
    0.42
    Activations Density 0.461%

    No Known Activations