© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 19-GEMMASCOPE-RES-16K
    6. 1557
    Prev
    Next
    INDEX
    Explanations

    the presence of numeric data or reference markers in a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CppCodeGen
    -1.01
    ArrowToggle
    -0.94
    webElementXpaths
    -0.93
     ſmall
    -0.91
    NameInMap
    -0.89
    ſelf
    -0.89
     ſeveral
    -0.86
     faſt
    -0.85
     fevere
    -0.81
     pleaſure
    -0.81
    POSITIVE LOGITS
     he
    0.59
     qui
    0.58
     to
    0.58
     can
    0.57
     He
    0.55
     It
    0.54
     must
    0.53
     ta
    0.53
     shall
    0.53
     will
    0.52
    Activations Density 0.241%

    No Known Activations