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. 16-GEMMASCOPE-RES-16K
    6. 3016
    Prev
    Next
    INDEX
    Explanations

    mentions of specific products and their attributes in a wholesale context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    manufacturing or production

    np_acts-logits-general · gemini-2.0-flash

    responsible manufacturing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     GetEnumerator
    -0.60
    providedIn
    -0.56
     transférez
    -0.55
     للمعارف
    -0.54
     élector
    -0.52
     MainAxisSize
    -0.52
    ErrUnexpectedEOF
    -0.51
    RefreshLayout
    -0.49
     Barbuda
    -0.48
     actes
    -0.47
    POSITIVE LOGITS
     manufacturing
    1.16
     production
    1.03
    manufacturing
    1.02
     manufacture
    0.98
     Manufacturing
    0.97
    Manufacturing
    0.94
     factories
    0.91
    Production
    0.90
    manufact
    0.87
    production
    0.87
    Activations Density 0.307%

    No Known Activations