© 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-2-2B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 1372
    Prev
    Next
    INDEX
    Explanations

    elements related to document structures and metadata, such as article types and forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Irvin
    -0.75
     Erskine
    -0.72
     Bertram
    -0.71
     Valenzuela
    -0.70
     Taft
    -0.69
     Hanne
    -0.69
     Norwich
    -0.68
     Hahn
    -0.66
    viii
    -0.65
     Norris
    -0.64
    POSITIVE LOGITS
     Barrett
    0.77
     Ellie
    0.72
     Foley
    0.68
     المعيارى
    0.67
     Ellison
    0.66
    Barrett
    0.65
     Wier
    0.64
     McKinnon
    0.64
     Burch
    0.62
     Krav
    0.62
    Activations Density 2.514%

    No Known Activations