© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 105937
    Prev
    Next
    INDEX
    Explanations

    mentions of organizations and formal announcements related to contracts and partnerships

    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
    fjspx
    -0.74
    parsedMessage
    -0.72
    ViewFeatures
    -0.54
    tagext
    -0.53
     saites
    -0.51
    CppMethod
    -0.51
     defaultstate
    -0.50
     AssemblyCulture
    -0.48
    ContentAlignment
    -0.48
    majánló
    -0.48
    POSITIVE LOGITS
    RegistryLite
    0.47
    PerformLayout
    0.41
     expectativas
    0.34
    tanleria
    0.33
     echi
    0.33
     ubiquitous
    0.33
     материалам
    0.32
    AccessException
    0.32
     esperaba
    0.31
    merkmale
    0.31
    Activations Density 0.026%

    No Known Activations