© 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. 11-GEMMASCOPE-RES-16K
    11. 2630
    Prev
    Next
    INDEX
    Explanations

    characters or symbols, particularly those related to formatting or special characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UCE
    -0.50
    ρης
    -0.48
    enic
    -0.47
     serie
    -0.46
    hé
    -0.46
     Erbe
    -0.46
     Bou
    -0.45
    clazz
    -0.45
    throp
    -0.43
     شم
    -0.43
    POSITIVE LOGITS
    #+#
    0.95
     AssemblyCulture
    0.85
    Chham
    0.82
     MainAxisSize
    0.82
     snippetHide
    0.81
     Paglinawan
    0.81
     defStyleAttr
    0.81
     Infórmanos
    0.78
    UserScript
    0.77
    GraphicsUnit
    0.77
    Activations Density 0.084%

    No Known Activations