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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 5-GEMMASCOPE-RES-16K
    6. 11374
    Prev
    Next
    INDEX
    Explanations

    programming-related syntax, especially variable assignments and method definitions

    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
    IUrlHelper
    -1.09
    ArrowToggle
    -0.83
     Савезне
    -0.77
    WireFormatLite
    -0.75
    aarrggbb
    -0.69
    WithIOException
    -0.68
     mourut
    -0.68
    IndentedString
    -0.67
    ьаж
    -0.67
    دانشنامهٔ
    -0.67
    POSITIVE LOGITS
    </th>
    0.70
     AssemblyTitle
    0.63
    </h4>
    0.63
    </h1>
    0.62
    </h6>
    0.62
    </td>
    0.61
    </h2>
    0.60
    ,
    0.57
    </h5>
    0.57
    )}</
    0.56
    Activations Density 0.622%

    No Known Activations