© 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. 18-GEMMASCOPE-RES-16K
    11. 8809
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Mat" and its various forms related to mathematics and programming libraries

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

    "Mat" followed by another token

    np_acts-logits-general · gemini-2.0-flash

    words starting with mat

    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
     فريبيس
    -0.67
    principalColumn
    -0.66
    OGND
    -0.64
     '\\;'
    -0.61
    oneofs
    -0.60
    таратура
    -0.58
    省市镇
    -0.58
    secutions
    -0.58
    ForValue
    -0.58
    vård
    -0.57
    POSITIVE LOGITS
     MAT
    1.05
    MAT
    0.97
    mat
    0.93
    Mat
    0.90
     Mat
    0.89
     mat
    0.85
     mati
    0.79
     mathe
    0.73
     Mats
    0.71
     Mati
    0.70
    Activations Density 0.085%

    No Known Activations