© 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. 31-GEMMASCOPE-RES-131K
    11. 36084
    Prev
    Next
    INDEX
    Explanations

    key features related to digital tools and applications

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

    features and functionalities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ➯
    -0.42
     BoxDecoration
    -0.34
    민
    -0.32
     mergeFrom
    -0.31
    scriptcase
    -0.31
     boisson
    -0.31
    PROPS
    -0.29
    Déf
    -0.28
    ScopeManager
    -0.27
     Erde
    -0.27
    POSITIVE LOGITS
     feature
    2.27
     features
    2.16
    feature
    1.95
     fitur
    1.93
     Features
    1.87
    features
    1.85
     Feature
    1.84
     functionality
    1.81
    Features
    1.77
    Feature
    1.75
    Activations Density 0.353%

    No Known Activations