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. 15-GEMMASCOPE-RES-16K
    6. 2240
    Prev
    Next
    INDEX
    Explanations

    web addresses and links

    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
    webElement
    -0.57
     ويكيميديا
    -0.55
    🔕
    -0.54
    andez
    -0.54
    webElementXpaths
    -0.53
    ➟
    -0.53
     turning
    -0.53
    pektrum
    -0.53
     sim
    -0.52
    QUIN
    -0.51
    POSITIVE LOGITS
    tagHelperRunner
    0.88
    enumi
    0.87
     <<<<<<<<<<<<<<
    0.78
     autorytatywna
    0.75
    RectangleBorder
    0.73
     محفوظة
    0.72
    Autoritní
    0.71
    MemoryWarning
    0.68
    UpInside
    0.65
    ContentLoaded
    0.64
    Activations Density 0.013%

    No Known Activations