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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 2040
    Prev
    Next
    INDEX
    Explanations

    occurrences of the prefix "Ma" and its variations

    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
    ंदीखरीदारी
    -0.67
    mobileqq
    -0.62
    Esa
    -0.60
    Toole
    -0.58
    contentLoaded
    -0.57
    TypeInfo
    -0.57
     Cæsar
    -0.57
     lenker
    -0.57
    Спасылкі
    -0.57
    FieldBuilder
    -0.56
    POSITIVE LOGITS
     Ma
    0.75
     Mapp
    0.71
     ma
    0.69
    Ma
    0.68
    ConstraintMaker
    0.66
     MA
    0.60
     Maiden
    0.59
    Mav
    0.59
     Mav
    0.58
     Mavericks
    0.58
    Activations Density 0.134%

    No Known Activations