© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 105075
    Prev
    Next
    INDEX
    Explanations

    references to challenges or obstacles related to availability or capacity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
    cèse
    -0.45
    makeText
    -0.41
     berech
    -0.40
    請繼續往下閱讀
    -0.40
     Berechnung
    -0.39
     blitt
    -0.39
     ſtate
    -0.38
    følgelig
    -0.38
     floors
    -0.37
     conforma
    -0.36
    POSITIVE LOGITS
    AndEndTag
    0.47
     Autorizaciones
    0.47
    rising
    0.47
     Seeder
    0.47
    tonode
    0.45
     Lied
    0.44
     rising
    0.44
    OGND
    0.43
    jgl
    0.42
    もしろ
    0.42
    Activations Density 0.059%

    No Known Activations