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. 12-GEMMASCOPE-RES-16K
    6. 6050
    Prev
    Next
    INDEX
    Explanations

    structured scientific or medical terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iredo
    -0.51
    __()
    -0.51
     parch
    -0.50
     GeoNames
    -0.49
     atuais
    -0.49
     corretamente
    -0.48
    avigation
    -0.48
     professionale
    -0.48
    Wired
    -0.48
     aikaa
    -0.48
    POSITIVE LOGITS
     iParam
    0.78
    
    0.68
     III
    0.68
    iParam
    0.68
    ANDUM
    0.67
    ⌘
    0.65
    EXTERN
    0.64
     Appendix
    0.62
     Affiliations
    0.61
     Subpart
    0.61
    Activations Density 0.641%

    No Known Activations