© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 93
    Prev
    Next
    INDEX
    Explanations

    elements related to programming syntax and mathematical expressions

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

    Mathematical or code-related symbols

    np_acts-logits-general · gemini-2.0-flash

    mathematical symbols and code constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    StoryboardSegue
    -0.79
    DockStyle
    -0.76
    SuspendLayout
    -0.70
     يتيمه
    -0.67
    +#+#
    -0.66
    NameInMap
    -0.65
    ✨:
    -0.63
     Zwer
    -0.63
     whoſe
    -0.61
    évaluateur
    -0.61
    POSITIVE LOGITS
     кӀ
    0.50
     تضيفلها
    0.48
    zarchiwizowane
    0.44
     verle
    0.44
     Процитовано
    0.44
    ాన
    0.43
    PyExc
    0.43
    ulta
    0.43
    melada
    0.43
    inda
    0.42
    Activations Density 1.075%

    No Known Activations