Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 14203
    Prev
    Next
    INDEX
    Explanations

    references to the term "Mat" or variations of it in a mathematical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Monfieur
    -1.04
     виправивши
    -1.03
     Anſ
    -0.97
     Diſ
    -0.97
     Efq
    -0.95
    Parcelize
    -0.95
    SequentialGroup
    -0.94
    DIPSETTING
    -0.88
     Eſ
    -0.88
    UserScript
    -0.85
    POSITIVE LOGITS
     mat
    2.58
    mat
    2.49
     Mat
    2.45
    Mat
    2.40
     MAT
    2.24
    MAT
    2.16
     mats
    2.10
    mats
    1.86
     Mats
    1.67
    Mats
    1.57
    Activations Density 0.080%

    No Known Activations