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-IT
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 16057
    Prev
    Next
    INDEX
    Explanations

    specific types of objects or products, particularly related to home goods and vehicles

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

    manufacturing of specific goods

    np_acts-logits-general · gemini-2.0-flash

    product makers and sellers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    InjectAttribute
    -0.44
    ViewInit
    -0.37
    GIVEREF
    -0.35
    webElementXpaths
    -0.33
    bitField
    -0.33
    onCreate
    -0.32
     śmier
    -0.32
     Normdatei
    -0.30
    原始内容存档于
    -0.30
     ingresar
    -0.29
    POSITIVE LOGITS
     maker
    0.93
     manufacturer
    0.93
     manufacturers
    0.92
     makers
    0.84
     distributor
    0.82
     supplier
    0.81
     industry
    0.81
     sellers
    0.79
     dealers
    0.79
     vendor
    0.78
    Activations Density 0.493%

    No Known Activations