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. 33-GEMMASCOPE-RES-131K
    6. 65760
    Prev
    Next
    INDEX
    Explanations

    names of places and geographical locations

    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_33/width_131k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gelieb
    -0.44
     Demokratie
    -0.41
     dumne
    -0.40
    FormState
    -0.40
    seiti
    -0.39
    roj
    -0.37
     couteau
    -0.37
    Etiquetas
    -0.36
    seitige
    -0.36
    const
    -0.36
    POSITIVE LOGITS
     يتيمه
    0.62
    rrggbb
    0.60
     Cumberland
    0.57
    umberland
    0.57
    Климат
    0.53
    :✨
    0.53
    rainian
    0.50
     referrerpolicy
    0.48
     AssemblyCompany
    0.47
     AssemblyCulture
    0.46
    Activations Density 0.003%

    No Known Activations