© 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. 13644
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "eller" and variations of the verb "teach."

    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
    IMPORTED
    -0.59
     MainAxisSize
    -0.56
    localVar
    -0.53
    出版年
    -0.52
     Савезне
    -0.52
     TType
    -0.52
    insatz
    -0.51
    icec
    -0.48
     يتيمه
    -0.48
    ষ্
    -0.48
    POSITIVE LOGITS
    eller
    0.86
     testimonials
    0.73
     yourselves
    0.70
     Theſe
    0.68
    BufferException
    0.66
    pois
    0.66
     doubtnut
    0.65
    DrawerToggle
    0.65
    femin
    0.64
     Dz
    0.64
    Activations Density 0.130%

    No Known Activations