© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 12512
    Prev
    Next
    INDEX
    Explanations

    JavaScript alert function calls and their parameters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ExtendWith
    -0.96
    UrlResolution
    -0.94
     ComVisible
    -0.93
     InputDecoration
    -0.87
    XmlAccessorType
    -0.86
    TagMode
    -0.86
    AddHtmlAttribute
    -0.85
     AssemblyCulture
    -0.83
    URLException
    -0.81
    клопе
    -0.80
    POSITIVE LOGITS
    <eos>
    0.83
    kek
    0.50
    ad
    0.49
     kasarigan
    0.47
     ad
    0.46
    列表
    0.46
    ier
    0.45
     pro
    0.45
     hek
    0.45
    مصادر
    0.44
    Activations Density 0.143%

    No Known Activations