© 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. 21-GEMMASCOPE-RES-16K
    11. 10576
    Prev
    Next
    INDEX
    Explanations

    phrases indicating functionality or effectiveness, particularly in relation to technology or software

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Caution
    -0.41
    atase
    -0.39
     Caution
    -0.39
    finement
    -0.39
    ylabel
    -0.39
    unhofer
    -0.39
    xlabel
    -0.38
    breadcrumb
    -0.37
    ništ
    -0.37
    fread
    -0.37
    POSITIVE LOGITS
     propOrder
    0.72
     fonctionner
    0.72
     funcionar
    0.70
     funcionamiento
    0.69
     funciona
    0.69
     fonctionnement
    0.68
    functioning
    0.68
     functioning
    0.68
    Worked
    0.66
     funziona
    0.65
    Activations Density 0.257%

    No Known Activations