© 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-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 36944
    Prev
    Next
    INDEX
    Explanations

    references to utility classes in Java programming

    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
    abstractmethod
    -0.63
    SpringBootTest
    -0.63
    ⓧ
    -0.57
    ſelf
    -0.57
     itſelf
    -0.48
     nameof
    -0.48
     OGSÅ
    -0.46
    seamnă
    -0.45
     joaat
    -0.45
     strerror
    -0.45
    POSITIVE LOGITS
     list
    0.73
     lists
    0.64
     List
    0.63
    ArrayList
    0.58
     collection
    0.54
     ArrayList
    0.54
    List
    0.53
    orderList
    0.53
    列表
    0.52
     Liste
    0.52
    Activations Density 0.002%

    No Known Activations