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. 15730
    Prev
    Next
    INDEX
    Explanations

    code snippets related to uploading and downloading images to and from a storage system

    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
     Мексичка
    -0.93
     pinulongan
    -0.88
    ValueStyle
    -0.84
     /*#__
    -0.73
     disambiguazione
    -0.69
     ब्रेकडाउन
    -0.69
    SourceChecksum
    -0.68
    NOPQRST
    -0.67
     Akismet
    -0.67
     CommonModule
    -0.67
    POSITIVE LOGITS
    val
    1.14
     val
    0.97
    let
    0.72
    println
    0.71
    VAL
    0.67
    print
    0.66
     print
    0.64
    Val
    0.62
    guard
    0.62
     Val
    0.60
    Activations Density 0.106%

    No Known Activations