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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 10-GEMMASCOPE-RES-16K
    6. 8397
    Prev
    Next
    INDEX
    Explanations

    HTTP method requests, specifically focusing on "GET" and "PUT" actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    isNullOrEmpty
    -0.55
    ностях
    -0.50
    Pyx
    -0.49
     uska
    -0.49
     ostavi
    -0.48
    Originally
    -0.47
    ucky
    -0.46
    tede
    -0.45
     PhpStorm
    -0.44
     שלי
    -0.44
    POSITIVE LOGITS
    GetMapping
    1.54
    HttpGet
    1.18
     doGet
    1.12
    AutoScale
    0.91
    ChildScrollView
    0.88
     GET
    0.87
    ftagPool
    0.86
    ViewFeatures
    0.85
     AssemblyCulture
    0.84
     Paglinawan
    0.82
    Activations Density 0.036%

    No Known Activations