© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 31640
    Prev
    Next
    INDEX
    Explanations

    punctuation and conjunctions in complex sentence structures

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    taken together

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    DockStyle
    -0.88
    SequentialGroup
    -0.78
    ConstraintMaker
    -0.71
     AssemblyCulture
    -0.69
    BeginInit
    -0.66
    sizeCache
    -0.66
    IntoConstraints
    -0.65
    ChildScrollView
    -0.64
    UrlResolution
    -0.62
    LookAnd
    -0.61
    POSITIVE LOGITS
     Overall
    1.50
    Overall
    1.48
     overall
    1.44
    overall
    1.38
    OVERALL
    1.11
    整體
    0.87
    gesamt
    0.85
     Altogether
    0.85
    总之
    0.81
    总体
    0.80
    Activations Density 0.177%

    No Known Activations