© 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. 34-GEMMASCOPE-RES-16K
    11. 1100
    Prev
    Next
    INDEX
    Explanations

    mathematical matrix notations and their relationships in the context of statistical models

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/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.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     <>",
    -0.65
     CreateTagHelper
    -0.63
     يتيمه
    -0.60
    новниш
    -0.59
     مشين
    -0.56
    rrggbb
    -0.54
    cillor
    -0.54
    Personensuche
    -0.52
    principalTable
    -0.51
    localctx
    -0.49
    POSITIVE LOGITS
     transpose
    0.90
     Trans
    0.86
    transpose
    0.81
     trans
    0.78
     transposed
    0.75
    Transpose
    0.75
    Trans
    0.73
    trans
    0.68
     TRAN
    0.65
     transposition
    0.65
    Activations Density 0.632%

    No Known Activations