© 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 EvalsExportsinterp-engineNEWAPI 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. 4851
    Prev
    Next
    INDEX
    Explanations

    the beginning of a new section or passage in the document

    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
     Quid
    -0.62
     Réponses
    -0.58
    featureID
    -0.56
    λον
    -0.52
     Riti
    -0.51
     kü
    -0.50
     Rede
    -0.50
    Sulf
    -0.50
     Pante
    -0.50
    ọc
    -0.50
    POSITIVE LOGITS
     Paglinawan
    0.76
     AssemblyCompany
    0.63
    出版年
    0.60
    ében
    0.59
    arikat
    0.54
     Infórmanos
    0.54
     &___
    0.53
    Cyfarwyddwr
    0.52
     typelib
    0.51
     NSError
    0.48
    Activations Density 0.138%

    No Known Activations