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. 12-GEMMASCOPE-RES-16K
    6. 10182
    Prev
    Next
    INDEX
    Explanations

    structured data formats and definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WebVitals
    -0.97
    Datuak
    -0.95
    Vidite
    -0.94
     estimés
    -0.94
    queryInterface
    -0.93
     pinulongan
    -0.93
    protoimpl
    -0.89
    ArrowToggle
    -0.89
     AssemblyCulture
    -0.88
    mybatisplus
    -0.88
    POSITIVE LOGITS
    invalidate
    0.45
    _
    0.41
    $\
    0.41
    ente
    0.41
     or
    0.40
    /
    0.39
    ua
    0.39
     Calling
    0.39
    nextInt
    0.38
    ю
    0.38
    Activations Density 2.034%

    No Known Activations