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-2-2B
    4. Residual Stream - 65k
    5. 20-GEMMASCOPE-RES-65K
    6. 880
    Prev
    Next
    INDEX
    Explanations

    keywords related to funding and support for scientific research and innovation

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

    references to government budget allocations and funding initiatives

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

    funding and budget allocations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     unknownFields
    -0.75
    ValueStyle
    -0.73
     disambiguazione
    -0.72
    CompleteListener
    -0.71
    تقاوى
    -0.69
    oredCriteria
    -0.69
     MessageBoxIcon
    -0.68
    abestanden
    -0.67
    ContentAsync
    -0.67
    ControllerAdvice
    -0.67
    POSITIVE LOGITS
     funding
    1.44
     allocation
    1.34
     allocations
    1.33
     allocated
    1.24
     allocating
    1.21
    funding
    1.21
     funds
    1.20
     allocate
    1.19
     appropriations
    1.18
     Funding
    1.12
    Activations Density 0.146%

    No Known Activations