© 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-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 125989
    Prev
    Next
    INDEX
    Explanations

    structure or formatting elements in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyCulture
    -0.56
    NameInMap
    -0.53
     '\\;'
    -0.51
    цездатний
    -0.49
    QMetaType
    -0.48
    gonic
    -0.47
     UserDao
    -0.47
    webElementXpaths
    -0.45
     ISNI
    -0.44
     ivelany
    -0.43
    POSITIVE LOGITS
    RegistryLite
    0.60
     JpaRepository
    0.54
    ➋
    0.43
    afficheront
    0.40
     haast
    0.37
     Kelle
    0.37
    OCCURRED
    0.37
    Бахар
    0.36
    ufnahme
    0.36
    BibitemOpen
    0.36
    Activations Density 0.200%

    No Known Activations