© 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 - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 9852
    Prev
    Next
    INDEX
    Explanations

    discussions around the concept of seriousness and the emotional weight of various subjects

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     "..\..\..\
    -0.91
     "..\..\
    -0.87
    RenderAtEndOf
    -0.73
    sizeCache
    -0.70
    HomeAsUpEnabled
    -0.69
     cellpadding
    -0.67
    WriteAttribute
    -0.66
    VersionUID
    -0.65
    SupportActionBar
    -0.65
     springfox
    -0.65
    POSITIVE LOGITS
     seriously
    1.83
     serious
    1.76
     seriousness
    1.60
     Serious
    1.57
    serious
    1.56
    seriously
    1.55
    Serious
    1.54
     serius
    1.51
     Seriously
    1.42
     sérieux
    1.38
    Activations Density 0.202%

    No Known Activations