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. 11290
    Prev
    Next
    INDEX
    Explanations

    terms related to computers and computer science

    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
    tagHelperRunner
    -0.79
    UrlResolution
    -0.78
    hasMoreElements
    -0.78
     tslint
    -0.77
    قایناق‌لار
    -0.75
     AssemblyTitle
    -0.74
    BufferException
    -0.74
    präche
    -0.74
     ویکی‌پدیا
    -0.72
     NSCoder
    -0.72
    POSITIVE LOGITS
    ised
    0.67
     Computer
    0.67
     COMPUTER
    0.62
     computador
    0.60
     pc
    0.59
    ized
    0.58
    computer
    0.57
    COMPUTER
    0.56
     computadora
    0.56
    PC
    0.56
    Activations Density 0.103%

    No Known Activations