© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 102662
    Prev
    Next
    INDEX
    Explanations

    key phrases indicating agreements or regulatory terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Special tokens or positions that mark transitions between different sections of text, often appearing near punctuation or at breaks in content flow.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
     Italijanski
    -0.64
    featureID
    -0.61
     CURIAM
    -0.60
    Aholisi
    -0.59
     surla
    -0.58
     كومونز
    -0.56
     Infórmanos
    -0.56
    
    -0.55
     okuyayım
    -0.54
    Derbyniad
    -0.54
    POSITIVE LOGITS
    <eos>
    0.38
     صوتيه
    0.34
     cherchés
    0.33
     yapı
    0.31
     soñ
    0.30
    bitField
    0.30
     EventArgs
    0.29
    하
    0.28
    possibly
    0.28
     Junior
    0.28
    Activations Density 0.127%

    No Known Activations