© 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-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 3088
    Prev
    Next
    INDEX
    Explanations

    modal verbs and their usage in complex sentences

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

    infinitive verb phrases introduced by "to".

    oai_token-act-pair · claude-4-5-haiku
    Triggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     proactively
    -0.70
     potentially
    -0.65
     officially
    -0.60
     hopefully
    -0.60
     excitedly
    -0.59
     typically
    -0.59
     automatically
    -0.59
     oficialmente
    -0.59
     finally
    -0.59
     easily
    -0.59
    POSITIVE LOGITS
    SequentialGroup
    0.69
    PerformLayout
    0.62
     NSCoder
    0.61
     arşivlendi
    0.58
    RenderAtEndOf
    0.57
    BeginInit
    0.57
    ToBounds
    0.57
     yyr
    0.57
    رشف
    0.56
    AnimationsModule
    0.56
    Activations Density 0.706%

    No Known Activations