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

    Neuronpedia

    APICircuit 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. 16-GEMMASCOPE-RES-16K
    6. 6172
    Prev
    Next
    INDEX
    Explanations

    mathematical structures or elements in equations and formulas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    InitVars
    -0.85
    GeneratedCode
    -0.85
     propOrder
    -0.83
     незавершена
    -0.83
    Дереккөздер
    -0.77
    XmlAccessorType
    -0.74
    AsUp
    -0.72
    expandindo
    -0.71
     referenties
    -0.71
    yntaxException
    -0.71
    POSITIVE LOGITS
    }{|
    0.69
    }{||
    0.59
     Beno
    0.52
     Naam
    0.50
    Prima
    0.49
    lsch
    0.48
     Silas
    0.48
    Aligned
    0.48
    ashimi
    0.47
    lative
    0.47
    Activations Density 0.009%

    No Known Activations