© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 8739
    Prev
    Next
    INDEX
    Explanations

    details regarding competition and sports achievements

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

    Follows words related to championships or tournaments

    np_acts-logits-general · gemini-2.0-flash

    international football tournaments

    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
    onaceous
    -0.62
    المناصب
    -0.61
     CITY
    -0.57
    Verein
    -0.56
     Unternehmer
    -0.55
     Midtown
    -0.55
     doanh
    -0.55
    봄
    -0.54
     City
    -0.54
     Ring
    -0.54
    POSITIVE LOGITS
    setVerticalGroup
    0.84
    Nazionale
    0.65
     nations
    0.61
    AndEndTag
    0.59
     referrerpolicy
    0.53
    цездатний
    0.53
     countries
    0.53
    LabelTagHelper
    0.51
    +#+
    0.50
    oneofs
    0.50
    Activations Density 0.061%

    No Known Activations