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. 32-GEMMASCOPE-RES-131K
    6. 129981
    Prev
    Next
    INDEX
    Explanations

    mentions of "Pirates" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    pirates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_32/width_131k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.32.hook_resid_post
    Hook Layer
    32
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagext
    -0.41
     Samar
    -0.41
    """)
    -0.40
    갖
    -0.40
    nya
    -0.40
    GOTREF
    -0.40
    ness
    -0.39
     Regard
    -0.39
    MSA
    -0.39
    m
    -0.37
    POSITIVE LOGITS
     Pirate
    0.69
    лтамалар
    0.68
     Pirates
    0.65
    Pirate
    0.65
    الحياه
    0.62
    Pirates
    0.60
     AssemblyCompany
    0.58
     pirate
    0.57
    ValueStyle
    0.56
     Pir
    0.55
    Activations Density 0.003%

    No Known Activations