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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 22-GEMMASCOPE-RES-16K
    6. 10439
    Prev
    Next
    INDEX
    Explanations

    corporate and product-related terms

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

    company activities

    np_acts-logits-general · gemini-2.0-flash

    invention and design

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     الحره
    -0.67
    ChildScrollView
    -0.52
    Organizer
    -0.52
     chi̍t
    -0.51
    Ecotoxicity
    -0.50
    urlpatterns
    -0.49
     fırs
    -0.49
     otomatig
    -0.49
    strtotime
    -0.48
    <_>
    -0.48
    POSITIVE LOGITS
     designing
    1.31
     manufacture
    1.26
     manufacturing
    1.26
     design
    1.18
     designers
    1.18
     engineers
    1.15
    Designing
    1.13
    研发
    1.11
    開発
    1.11
     inventing
    1.09
    Activations Density 0.480%

    No Known Activations