© 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. 14530
    Prev
    Next
    INDEX
    Explanations

    references to entrepreneurs and their successful ventures

    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
     ect
    -0.57
     Afterward
    -0.57
    存于互联网档案馆
    -0.51
     plow
    -0.48
     afterward
    -0.48
     saveiro
    -0.46
    Canceled
    -0.45
    Concerning
    -0.45
     favoris
    -0.44
    stacles
    -0.43
    POSITIVE LOGITS
     learnt
    0.86
     irrespective
    0.81
     spoilt
    0.74
     erst
    0.74
     Incidentally
    0.72
     artistes
    0.71
     envisaged
    0.67
     Bengaluru
    0.65
     hence
    0.64
     spelt
    0.64
    Activations Density 0.722%

    No Known Activations