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. 0-GEMMASCOPE-RES-16K
    6. 3406
    Prev
    Next
    INDEX
    Explanations

    code elements related to structured data definitions and their properties in a programming context, particularly focusing on the Protobuf library

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    les
    -0.46
     Agnew
    -0.45
    lüssel
    -0.43
     Gier
    -0.42
     Otherwise
    -0.41
     القديمة
    -0.41
     Act
    -0.41
    ガニック
    -0.41
    Otherwise
    -0.40
     otherwise
    -0.40
    POSITIVE LOGITS
    FieldBuilder
    1.05
    Datuak
    0.99
    iprot
    0.91
    SourceChecksum
    0.90
     Audiodateien
    0.90
     }{@
    0.89
    GEBURTSDATUM
    0.85
    AccessorTable
    0.85
    tagHelperRunner
    0.85
    IndentedString
    0.84
    Activations Density 2.433%

    No Known Activations