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. 9798
    Prev
    Next
    INDEX
    Explanations

    sports-related events and statistics

    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
     special
    -0.55
     pratique
    -0.52
    ทั่ว
    -0.48
     periodi
    -0.48
    躇
    -0.47
    graphicx
    -0.46
     unique
    -0.46
     many
    -0.46
     специальные
    -0.45
     basic
    -0.45
    POSITIVE LOGITS
    <bos>
    1.11
    ArrowToggle
    0.88
     chased
    0.81
    Tikang
    0.78
    SharedDtor
    0.78
    енча
    0.69
    piram
    0.68
    oredCriteria
    0.68
    Chham
    0.67
     Tapatalk
    0.66
    Activations Density 0.175%

    No Known Activations