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. 5-GEMMASCOPE-RES-16K
    6. 3933
    Prev
    Next
    INDEX
    Explanations

    medical terms and phrases related to conditions affecting the digestive and urinary systems, as well as treatments for various disorders

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ArrowToggle
    -0.70
    новништво
    -0.66
     وتسجيلات
    -0.56
    DockStyle
    -0.53
    Brainz
    -0.52
    efeller
    -0.51
    twór
    -0.51
     OBITUARY
    -0.51
    StoryboardSegue
    -0.50
     Penh
    -0.48
    POSITIVE LOGITS
     acne
    0.87
    Acne
    0.83
     Acne
    0.74
    continence
    0.71
     erec
    0.70
     menopause
    0.69
     incontinence
    0.67
     cys
    0.63
    ケート
    0.62
    acne
    0.61
    Activations Density 0.641%

    No Known Activations