© 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. 22-GEMMASCOPE-RES-16K
    11. 11725
    Prev
    Next
    INDEX
    Explanations

    special characters and spaces in structured data formats

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     enfans
    -0.61
    berdayakan
    -0.53
     alemania
    -0.48
    hæng
    -0.48
     ainfi
    -0.47
     étoient
    -0.47
     pérd
    -0.47
     zitate
    -0.46
     zijne
    -0.46
    medriver
    -0.46
    POSITIVE LOGITS
    uxxxx
    0.70
     Biôgrafia
    0.66
     Италијани
    0.59
    abestanden
    0.58
    AndroidJUnit
    0.56
    oa̍t
    0.56
    RegressionTest
    0.55
    featureID
    0.55
     Савезне
    0.54
     Мексичка
    0.54
    Activations Density 1.682%

    No Known Activations