© 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. 11-GEMMASCOPE-RES-16K
    11. 13101
    Prev
    Next
    INDEX
    Explanations

    elements related to software and technology discussions, particularly about Ubuntu and system configurations

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/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.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     виправивши
    -0.64
    цездатний
    -0.57
    rungsseite
    -0.54
     Réponses
    -0.52
     CreateTagHelper
    -0.51
     ostavi
    -0.48
     XNUMX
    -0.46
    THISDAY
    -0.45
    المشاركات
    -0.45
    RUnlock
    -0.45
    POSITIVE LOGITS
     diaria
    0.40
     ibunya
    0.39
     financière
    0.39
    altezza
    0.38
    மு
    0.37
     jabón
    0.37
     quelconque
    0.37
     Erst
    0.37
    épaisseur
    0.35
     sienta
    0.35
    Activations Density 12.220%

    No Known Activations