© 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. 17-GEMMASCOPE-RES-16K
    11. 11624
    Prev
    Next
    INDEX
    Explanations

    references to legal and regulatory terms or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     سكانية
    -1.01
    ArrowToggle
    -0.90
    AddTagHelper
    -0.87
    pendente
    -0.81
    karz
    -0.80
     calendriers
    -0.79
     gainera
    -0.77
    öbb
    -0.77
    orenje
    -0.76
     defaultstate
    -0.73
    POSITIVE LOGITS
    teen
    0.94
    ous
    0.85
    🏻
    0.85
    ers
    0.80
    🏼
    0.79
    er
    0.78
    ment
    0.78
    ed
    0.77
     Diſ
    0.76
    ing
    0.76
    Activations Density 1.563%

    No Known Activations