© 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. 9907
    Prev
    Next
    INDEX
    Explanations

    references to articles and comments in a structured format

    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
    +#+#
    -0.99
     AssemblyCulture
    -0.90
    principalColumn
    -0.88
    PerformLayout
    -0.85
    endphp
    -0.81
    complexContent
    -0.81
    IntoConstraints
    -0.80
     Italijani
    -0.80
     ujednoznacz
    -0.78
    parsedMessage
    -0.77
    POSITIVE LOGITS
    idp
    0.50
    IfExists
    0.50
     Haupt
    0.47
    idad
    0.46
     correctes
    0.45
    说过
    0.45
    ensatz
    0.44
     entendre
    0.44
     spot
    0.44
     main
    0.43
    Activations Density 0.461%

    No Known Activations