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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 104326
    Prev
    Next
    INDEX
    Explanations

    punctuation and stop symbols

    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
     joaat
    -0.41
    ahue
    -0.40
     Skyl
    -0.40
    mità
    -0.39
     rés
    -0.39
    desliz
    -0.39
    Jegyzetek
    -0.38
    chiere
    -0.38
    SITE
    -0.37
    Pranala
    -0.37
    POSITIVE LOGITS
     propOrder
    0.66
     <>",
    0.61
     ModelExpression
    0.61
    principalTable
    0.56
    XtraReports
    0.52
    EDEFAULT
    0.52
    帖最后由
    0.52
     Савезне
    0.51
    AutoField
    0.51
    Personendaten
    0.51
    Activations Density 0.010%

    No Known Activations