© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 3-GEMMASCOPE-RES-16K
    11. 15829
    Prev
    Next
    INDEX
    Explanations

    specific scientific terms and phrases related to biological or medical research

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     مرئيه
    -1.06
     AssemblyTitle
    -0.88
     évêque
    -0.83
    featureID
    -0.76
    adeloupe
    -0.75
    WriteLiteral
    -0.74
    URLException
    -0.73
     onCreateView
    -0.70
    prepareStatement
    -0.69
     crocodiles
    -0.69
    POSITIVE LOGITS
     commemorative
    0.75
     consolation
    0.70
    dummy
    0.70
    '],
    0.68
     dummy
    0.67
     filler
    0.67
    Introductory
    0.66
     celebratory
    0.64
     Preparatory
    0.64
    ngdoc
    0.64
    Activations Density 2.513%

    No Known Activations