© 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. 104282
    Prev
    Next
    INDEX
    Explanations

    segments related to XML specifications and configurations

    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
    IndentedString
    -0.72
     estekak
    -0.69
    новништво
    -0.69
     resourceCulture
    -0.64
    Personendaten
    -0.57
    AndEndTag
    -0.56
     '\\;'
    -0.55
    ValueGeneration
    -0.54
    rungsseite
    -0.53
    awtextra
    -0.53
    POSITIVE LOGITS
    onaceous
    0.34
     root
    0.33
     labor
    0.33
    addMouseListener
    0.32
    stanza
    0.31
    vocable
    0.30
     numerical
    0.30
    oupe
    0.30
     rumored
    0.30
    root
    0.29
    Activations Density 0.122%

    No Known Activations