© 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-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 10245
    Prev
    Next
    INDEX
    Explanations

    references to features in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     PVA
    -0.87
     pessoais
    -0.87
    ]^{-
    -0.86
     clearColor
    -0.83
    RemoteException
    -0.83
     LDA
    -0.82
     ALP
    -0.81
     nôtre
    -0.81
    idp
    -0.81
     pregunto
    -0.80
    POSITIVE LOGITS
     features
    1.82
     feature
    1.63
     Features
    1.54
    features
    1.52
    Features
    1.49
     FEATURE
    1.47
     Feature
    1.43
     FEATURES
    1.37
    Feature
    1.33
    feature
    1.32
    Activations Density 0.045%

    No Known Activations