© 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. 27-GEMMASCOPE-RES-16K
    11. 6723
    Prev
    Next
    INDEX
    Explanations

    evaluations of narrative clarity and character development in films

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     EconPapers
    -0.54
    ValueStyle
    -0.52
    ThroughAttribute
    -0.49
     مشين
    -0.49
    RectangleBorder
    -0.47
     surla
    -0.47
    大変
    -0.44
    PYX
    -0.44
     незавершена
    -0.41
     noDo
    -0.40
    POSITIVE LOGITS
     uninteresting
    0.81
     bland
    0.80
     boring
    0.75
     unnecessarily
    0.71
     dull
    0.70
     unnecessary
    0.70
     awkwardly
    0.69
     underwhelming
    0.68
     drab
    0.67
     mediocrity
    0.65
    Activations Density 0.285%

    No Known Activations