© 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-2-2B
    7. Residual Stream - 16k
    9. 6-GEMMASCOPE-RES-16K
    11. 15613
    Prev
    Next
    INDEX
    Explanations

    specific characters and words in various languages, particularly focusing on those that denote or refer to concepts related to file structures and content

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     mxArray
    -1.04
     تضيفلها
    -0.81
     createStore
    -0.79
    aarrggbb
    -0.74
     ApiException
    -0.73
     createSprite
    -0.73
     виправивши
    -0.69
     geslacht
    -0.69
     onPostExecute
    -0.68
    국의
    -0.68
    POSITIVE LOGITS
     Cæsar
    0.82
    ohjel
    0.73
     Inſ
    0.72
     popoli
    0.71
     Reſ
    0.70
     Conſ
    0.70
     Hift
    0.70
     JIT
    0.69
     kuiten
    0.67
     inſ
    0.67
    Activations Density 0.105%

    No Known Activations