© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 15-GEMMASCOPE-RES-16K
    11. 11168
    Prev
    Next
    INDEX
    Explanations

    C++ template definitions and their associated syntax

    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
    EventQueue
    -0.55
     InputDecoration
    -0.51
     sha
    -0.50
    makeText
    -0.50
     فريبيس
    -0.49
     sent
    -0.49
    IBOutlet
    -0.48
    vaadin
    -0.48
    VIAF
    -0.48
    izielle
    -0.46
    POSITIVE LOGITS
     betweenstory
    0.87
     disambiguazione
    0.75
     propOrder
    0.74
    曖昧さ回避
    0.72
    typeparam
    0.72
    RegistryLite
    0.66
    ISupport
    0.63
    SBATCH
    0.63
     Infórmanos
    0.62
     myſelf
    0.60
    Activations Density 0.049%

    No Known Activations