© 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. 12696
    Prev
    Next
    INDEX
    Explanations

    references to documents and files, including their formats and details

    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
    DetailActivity
    -0.42
     arşivlendi
    -0.41
    PushMatrix
    -0.39
     Winkel
    -0.39
     BoxDecoration
    -0.38
     hasard
    -0.38
     Majefty
    -0.38
    eterangan
    -0.38
     besos
    -0.38
     placements
    -0.37
    POSITIVE LOGITS
     length
    1.21
     size
    1.09
     Length
    1.01
    length
    0.98
    Length
    0.93
     LENGTH
    0.92
     sized
    0.91
     lenght
    0.90
    長さ
    0.90
    Size
    0.90
    Activations Density 0.521%

    No Known Activations