© 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. 50900
    Prev
    Next
    INDEX
    Explanations

    programming-related terms and concepts, particularly those associated with Java and the .NET System.Reflection namespace

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    assemblies and reflection

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    UnusedPrivate
    -0.80
    webElementXpaths
    -0.63
    AddHtmlAttribute
    -0.56
    +#+#
    -0.53
    fromnode
    -0.52
     يتيمه
    -0.48
    tagHelperRunner
    -0.45
     pinulongan
    -0.43
     invokingState
    -0.43
    AccessorTable
    -0.42
    POSITIVE LOGITS
    Referencias
    0.49
     jsonData
    0.45
    Hentet
    0.45
    antin
    0.44
    Fel
    0.43
     books
    0.42
     autor
    0.41
     bookId
    0.40
     reper
    0.40
    FEL
    0.40
    Activations Density 0.002%

    No Known Activations