© 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. 0-GEMMASCOPE-RES-65K
    11. 6592
    Prev
    Next
    INDEX
    Explanations

    words related to "area" or "areas" in a technical context, likely associated with graphical or spatial dimensions

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     Monfieur
    -0.97
     pleaſure
    -0.78
     raiſ
    -0.77
     poffible
    -0.74
     Diſ
    -0.68
     Efq
    -0.67
     Eſ
    -0.67
     vervol
    -0.67
     poffe
    -0.66
    __":
    -0.65
    POSITIVE LOGITS
     saites
    0.75
    TimeoutException
    0.72
     Areas
    0.66
     Roskov
    0.65
    Pageable
    0.62
     AREAS
    0.62
    areas
    0.62
    provoking
    0.61
    Климат
    0.60
    TypedDataSet
    0.60
    Activations Density 0.087%

    No Known Activations