© 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. 15-GEMMASCOPE-RES-16K
    11. 5947
    Prev
    Next
    INDEX
    Explanations

    symbols and mathematical notations used in various types of formatted expressions

    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
    HasAnnotation
    -0.90
     Himo
    -0.81
     createState
    -0.80
    tonsoft
    -0.79
    Hochspringen
    -0.73
    TargetException
    -0.73
     BorderRadius
    -0.73
    ChildScrollView
    -0.72
     BrowserModule
    -0.72
    WebMethod
    -0.71
    POSITIVE LOGITS
    بالإنجليزية
    0.68
    最快更新
    0.55
     zvuky
    0.54
     suficientes
    0.53
     grammi
    0.52
     trous
    0.52
    øya
    0.52
    떻
    0.52
     kerül
    0.51
     Quelles
    0.51
    Activations Density 1.281%

    No Known Activations