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. 20-GEMMASCOPE-RES-16K
    6. 12884
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to pensions and retirement plans

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     lenker
    -0.59
     joaat
    -0.51
    
    -0.44
    Personendaten
    -0.43
     uLocal
    -0.43
    RTSC
    -0.42
    borde
    -0.42
     prijs
    -0.42
    webElementXpaths
    -0.42
    Árbitro
    -0.41
    POSITIVE LOGITS
     pension
    0.77
    Pension
    0.64
     pensions
    0.63
     Pension
    0.62
     retirement
    0.59
     employee
    0.53
    pension
    0.53
    Retirement
    0.53
    retirement
    0.50
     benefits
    0.49
    Activations Density 0.157%

    No Known Activations