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. 9278
    Prev
    Next
    INDEX
    Explanations

    references to mechanical issues and repair services

    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
     CreateTagHelper
    -0.71
     snippetHide
    -0.69
    Amicalement
    -0.68
    Дереккөздер
    -0.66
    новништво
    -0.64
    Cyfeiriadau
    -0.63
     intptr
    -0.63
    tvguidetime
    -0.62
    Numerology
    -0.61
     scattata
    -0.61
    POSITIVE LOGITS
     maintenance
    0.70
     repair
    0.69
     repairs
    0.66
    исправ
    0.65
     troubleshooting
    0.63
    故障
    0.62
    repair
    0.62
     malfunctions
    0.61
     malfunction
    0.60
     mechanical
    0.60
    Activations Density 0.280%

    No Known Activations