© 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. 116763
    Prev
    Next
    INDEX
    Explanations

    formatted strings or patterns in programming code

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
     ModelExpression
    -0.70
    iſen
    -0.58
     оригіналу
    -0.56
    ſcher
    -0.55
    enumii
    -0.54
    iſten
    -0.52
    AsUp
    -0.51
     CreateTagHelper
    -0.50
    AutoScaleMode
    -0.49
     BoxFit
    -0.49
    POSITIVE LOGITS
    richTextPanel
    0.43
    tvguidetime
    0.38
    Millis
    0.35
    MockBean
    0.35
     Савезне
    0.34
     européennes
    0.32
    Carreira
    0.32
    pters
    0.32
     rejoindre
    0.32
    swire
    0.31
    Activations Density 0.037%

    No Known Activations