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. 130001
    Prev
    Next
    INDEX
    Explanations

    content related to construction and building activities

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

    constructing structures

    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
     EconPapers
    -0.66
    HideFlags
    -0.56
    HtmlAttribute
    -0.54
     AssemblyCompany
    -0.53
     ancien
    -0.53
     gammel
    -0.53
     antiguos
    -0.52
     antiga
    -0.52
     anciens
    -0.50
    ValueStyle
    -0.50
    POSITIVE LOGITS
     tunnels
    0.64
     houses
    0.64
     bridges
    0.63
     roads
    0.63
     cabins
    0.61
     shelters
    0.59
     dams
    0.58
     classrooms
    0.57
     toilets
    0.57
     buildings
    0.57
    Activations Density 0.028%

    No Known Activations