© 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 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. 125009
    Prev
    Next
    INDEX
    Explanations

    technical terms and specifications related to safety systems and technologies

    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
    ChildScrollView
    -0.35
    Dead
    -0.31
    Yeah
    -0.30
     yeah
    -0.29
     Yeah
    -0.28
     dead
    -0.28
     Dead
    -0.28
    셜
    -0.28
     profession
    -0.28
    Transfer
    -0.27
    POSITIVE LOGITS
     AssemblyCulture
    0.74
     ब्रेकडाउन
    0.65
    oa̍t
    0.59
    Искәрмәләр
    0.58
    ArrowToggle
    0.57
    RenderAtEndOf
    0.57
     manufacturers
    0.57
    LabelTagHelper
    0.57
    ImageContext
    0.57
    infant
    0.55
    Activations Density 0.038%

    No Known Activations