© 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. 63950
    Prev
    Next
    INDEX
    Explanations

    coding-related keywords or flags associated with error handling and game object properties

    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
     snippetHide
    -0.57
    DockStyle
    -0.46
    Checks
    -0.45
    Kanpo
    -0.43
    abstractmethod
    -0.40
     checks
    -0.37
    InputTagHelper
    -0.37
     Checks
    -0.35
    checks
    -0.35
    Geplaatst
    -0.35
    POSITIVE LOGITS
    Vanjske
    3.45
    Eksterne
    1.52
    :][
    1.43
    currentColor
    1.43
     Ressource
    0.97
    loài
    0.96
     Ressources
    0.95
    Externí
    0.92
    外部リンク
    0.91
    Spoljašnje
    0.88
    Activations Density 0.000%

    No Known Activations