Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 8095
    Prev
    Next
    INDEX
    Explanations

    references to the release and publication history of works or projects

    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
     MediatR
    -0.37
     precin
    -0.35
    addField
    -0.34
     preload
    -0.33
    MethodManager
    -0.33
     Meda
    -0.33
    UnsafeEnabled
    -0.32
     newBuilder
    -0.32
     hoe
    -0.31
     Purple
    -0.31
    POSITIVE LOGITS
     propOrder
    0.83
     AssemblyVersion
    0.57
     originalmente
    0.52
     <>",
    0.51
    complexType
    0.49
    originally
    0.47
     originally
    0.47
    earlier
    0.47
     tidigare
    0.46
    ของคุณ
    0.44
    Activations Density 0.041%

    No Known Activations