© 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. 20-GEMMASCOPE-RES-16K
    11. 13104
    Prev
    Next
    INDEX
    Explanations

    terms related to legal and governmental processes, especially concerning evidence, testimony, and compensation claims

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

    before "department," "commission," "co," "company," or "works"

    np_acts-logits-general · gemini-2.0-flash

    lawsuit and business entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     onboarding
    -0.62
     puțin
    -0.61
    IQR
    -0.60
     Assignee
    -0.60
    yaszt
    -0.60
     digital
    -0.58
     digitally
    -0.58
    behaviors
    -0.57
     midline
    -0.56
     playbook
    -0.56
    POSITIVE LOGITS
    luß
    0.65
    -]
    0.63
     muß
    0.63
     mußte
    0.61
     daß
    0.58
     skall
    0.57
     müßte
    0.56
     mußten
    0.55
     NDEBUG
    0.55
    ThemeOverlay
    0.54
    Activations Density 0.847%

    No Known Activations