© 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. 31908
    Prev
    Next
    INDEX
    Explanations

    references to additional or extra components

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

    extra or additional items

    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
    @[+][
    -0.68
    DOCTYPE
    -0.62
     AssemblyCompany
    -0.61
    //
    -0.60
     préférence
    -0.58
     tramonto
    -0.57
    tymologie
    -0.57
     verschill
    -0.56
     nonatomic
    -0.56
     exactement
    -0.55
    POSITIVE LOGITS
     extra
    0.82
    extra
    0.72
     EXTRA
    0.70
    Extra
    0.70
     Extra
    0.70
    нительно
    0.68
    EXTRA
    0.68
    Extras
    0.60
    额外
    0.60
     added
    0.59
    Activations Density 0.117%

    No Known Activations