© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 17-GEMMASCOPE-RES-16K
    6. 4373
    Prev
    Next
    INDEX
    Explanations

    terms related to maintenance and servicing procedures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rowspan
    -0.52
    queryInterface
    -0.52
    sertation
    -0.52
    ętr
    -0.50
    debut
    -0.49
    ंदीखरीदारी
    -0.48
    OfBirth
    -0.48
    disambiguation
    -0.48
    GEBURTSDATUM
    -0.47
    finale
    -0.45
    POSITIVE LOGITS
     periodic
    1.36
     Periodic
    1.31
     yearly
    1.30
    Periodic
    1.29
     periodically
    1.27
    periodic
    1.20
     periodical
    1.18
     annual
    1.15
     regularly
    1.13
     annually
    1.13
    Activations Density 0.302%

    No Known Activations