© 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. 15-GEMMASCOPE-RES-16K
    6. 9440
    Prev
    Next
    INDEX
    Explanations

    specific terms related to monitoring and tracking activities or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/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.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    følgelig
    -0.74
    zości
    -0.52
     geldig
    -0.50
    adering
    -0.49
     chegando
    -0.48
    jahtera
    -0.47
    ử
    -0.46
     recientes
    -0.46
    ďaka
    -0.46
    håll
    -0.45
    POSITIVE LOGITS
    InjectAttribute
    0.79
     تضيفلها
    0.79
     typelib
    0.77
    basicConfig
    0.72
    RegistryLite
    0.70
     snippetHide
    0.67
     while
    0.67
     whilst
    0.64
    Gambas
    0.62
     transfieras
    0.62
    Activations Density 0.642%

    No Known Activations