© 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. 22-GEMMASCOPE-RES-16K
    11. 11362
    Prev
    Next
    INDEX
    Explanations

    unique identifiers or codes

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

    Follows a hyphen

    np_acts-logits-general · gemini-2.0-flash

    a variety of specific tokens

    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
     ویکی‌پدیا
    -0.72
     médicaux
    -0.62
    存于互联网档案馆
    -0.61
    اقرأ
    -0.61
    AndEndTag
    -0.61
     industriels
    -0.59
    ЧИТА
    -0.58
     dentaire
    -0.57
    Ayrıca
    -0.57
     imageNamed
    -0.56
    POSITIVE LOGITS
    Autoritní
    0.77
    RunAsync
    0.61
     👋
    0.60
     
    0.60
    adaptiveStyles
    0.54
    InvalidProtocol
    0.47
     The
    0.47
     In
    0.47
     createState
    0.46
    buzo
    0.45
    Activations Density 0.247%

    No Known Activations