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 - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 2612
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to marketing and promotional activities

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

    Marketing and promotion

    np_acts-logits-general · gemini-2.0-flash

    promotional marketing campaigns

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
     aDecoder
    -0.57
     Form
    -0.51
    дя
    -0.49
    oforms
    -0.48
     FORM
    -0.48
    Референце
    -0.48
     y
    -0.47
    
    -0.47
     CGPoint
    -0.47
     TestBed
    -0.46
    POSITIVE LOGITS
     campaigns
    1.06
     themſelves
    0.92
     Campaigns
    0.90
     campaign
    0.88
     slogans
    0.86
     myſelf
    0.84
     raiſ
    0.80
     himſelf
    0.79
    campaigns
    0.79
     againſt
    0.78
    Activations Density 0.104%

    No Known Activations