© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 53254
    Prev
    Next
    INDEX
    Explanations

    HTML or XML elements and their attributes in a structured format

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    :✨
    -0.73
    SBATCH
    -0.60
     wireType
    -0.60
    ackerel
    -0.59
    uxxxx
    -0.59
    AddTagHelper
    -0.57
     intptr
    -0.57
     HttpNotFound
    -0.54
    principalColumn
    -0.54
    帖最后由
    -0.54
    POSITIVE LOGITS
    .
    0.37
     zo
    0.34
     registered
    0.34
    nyataan
    0.33
    脚注の使い方
    0.32
     рада
    0.31
    Later
    0.29
     packed
    0.29
    ↵↵
    0.29
    sys
    0.29
    Activations Density 0.005%

    No Known Activations