© 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. 15-GEMMASCOPE-RES-16K
    11. 2082
    Prev
    Next
    INDEX
    Explanations

    details related to the life and personal characteristics of an individual, particularly regarding their contributions or legacy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/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.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inį
    -0.60
     appui
    -0.56
    MENAFN
    -0.54
     somebody
    -0.54
    dpa
    -0.53
     alltså
    -0.53
    umą
    -0.52
     amanhã
    -0.52
    írus
    -0.49
     vectorielles
    -0.49
    POSITIVE LOGITS
     otomatig
    0.73
     betweenstory
    0.73
    terscotch
    0.67
     gelieb
    0.67
    invokeLater
    0.67
     loved
    0.64
    IsContent
    0.64
     grandkids
    0.63
    Begriffsklä
    0.62
    ChildIndex
    0.61
    Activations Density 0.044%

    No Known Activations