Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 9-GEMMASCOPE-RES-16K
    6. 1427
    Prev
    Next
    INDEX
    Explanations

    terms related to elections and cycles in governance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    HEAST
    -0.49
     provisoire
    -0.48
     temporaire
    -0.45
    JoinColumn
    -0.43
     fonti
    -0.43
    XmlType
    -0.42
     disambiguazione
    -0.42
    Források
    -0.41
    кт
    -0.41
     prisa
    -0.40
    POSITIVE LOGITS
     незавершена
    0.78
    Atsauces
    0.69
    BagConstraints
    0.68
     session
    0.68
     Paglinawan
    0.67
    cycles
    0.62
    تقاوى
    0.61
     calendriers
    0.61
    oplasty
    0.61
     '\\;'
    0.60
    Activations Density 0.391%

    No Known Activations