© 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. 33-GEMMASCOPE-RES-16K
    11. 3340
    Prev
    Next
    INDEX
    Explanations

    terms related to academic research and analysis

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/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.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    bootstrapcdn
    -0.53
    AsUp
    -0.51
    EndContext
    -0.49
     inability
    -0.44
     MainAxisSize
    -0.43
     ThemeData
    -0.39
     aucune
    -0.39
    রণ
    -0.35
    abestanden
    -0.34
     aucun
    -0.34
    POSITIVE LOGITS
     not
    2.22
     nejen
    2.14
    不仅
    2.02
    不僅
    1.92
    不仅仅
    1.83
    不但
    1.73
    not
    1.54
     both
    1.53
     bukan
    1.51
     zarówno
    1.51
    Activations Density 1.623%

    No Known Activations