© 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 - 16k
    9. 40-GEMMASCOPE-RES-16K
    11. 5705
    Prev
    Next
    INDEX
    Explanations

    elements related to historical disputes and significant political events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GOTREF
    -0.52
     AssemblyCompany
    -0.50
    studied
    -0.50
    ViewImports
    -0.50
    MemoryWarning
    -0.49
     Studied
    -0.49
    rungsseite
    -0.48
    visited
    -0.47
    :✨
    -0.47
     studied
    -0.46
    POSITIVE LOGITS
     led
    1.55
     helped
    1.44
     enabled
    1.42
     caused
    1.40
     allowed
    1.27
     contributed
    1.24
     resulted
    1.23
     prompted
    1.22
     brought
    1.21
     prevented
    1.21
    Activations Density 1.305%

    No Known Activations