© 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. 5953
    Prev
    Next
    INDEX
    Explanations

    mathematical representations and formatting, especially in the context of vector and matrix notation typically found in linear algebra and statistics

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

    Text containing bold symbols/vectors

    np_acts-logits-general · gemini-2.0-flash

    \mathbf{ followed by {

    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
    MethodManager
    -0.67
     @"/
    -0.67
     '{@
    -0.65
    AsUp
    -0.63
    FunctionFlags
    -0.62
    findpost
    -0.61
    tabular
    -0.57
    KommentareTeilen
    -0.57
    SuspendLayout
    -0.57
    ValueGeneration
    -0.56
    POSITIVE LOGITS
    liesslich
    0.66
     ControllerBase
    0.56
     Waray
    0.56
     חיצוניים
    0.55
    ">
    0.54
     Corpor
    0.53
     Pho
    0.51
     beetje
    0.51
    ']").
    0.50
    nsic
    0.49
    Activations Density 0.219%

    No Known Activations