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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 251
    Prev
    Next
    INDEX
    Explanations

    references to events and showcases within the technology and innovation sectors

    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
    RefreshLayout
    -0.50
     sẻ
    -0.49
    het
    -0.44
     clear
    -0.43
    ска
    -0.43
    RESET
    -0.42
    que
    -0.41
    clear
    -0.41
    usda
    -0.41
     bassa
    -0.40
    POSITIVE LOGITS
     companies
    1.26
     businesses
    1.24
     vendors
    1.20
    companies
    1.13
     manufacturers
    1.13
     firms
    1.12
    businesses
    1.10
     exhibitors
    1.09
    Companies
    1.06
     Companies
    1.03
    Activations Density 0.243%

    No Known Activations