© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 9063
    Prev
    Next
    INDEX
    Explanations

    sequence and structure in data or coding formats

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

    Preceding reference markers ([@, ref, etc.)

    np_acts-logits-general · gemini-2.0-flash

    degree Celsius symbols

    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
    -0.69
     ***!
    -0.63
    Tazama
    -0.61
     Paglinawan
    -0.61
    etheless
    -0.57
    complexContent
    -0.57
     sanitaires
    -0.57
     contextLoads
    -0.56
    retudo
    -0.55
    ProcessEvent
    -0.54
    POSITIVE LOGITS
     Audiodateien
    0.64
    multirow
    0.58
    UserScript
    0.56
    RenderAtEndOf
    0.56
    expandindo
    0.52
    <bos>
    0.52
    日閲覧
    0.51
     AssemblyProduct
    0.50
    UrlResolution
    0.48
    Autoritní
    0.48
    Activations Density 0.323%

    No Known Activations