Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 17-GEMMASCOPE-RES-16K
    6. 10874
    Prev
    Next
    INDEX
    Explanations

    references to entities related to biological systems, structures, and their functions within the context of various domains

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    InputBorder
    -0.73
    UnsafeEnabled
    -0.64
     Infórmanos
    -0.62
    хьтан
    -0.60
    ̀
    -0.60
    }/{
    -0.58
    tanleria
    -0.58
    IBarButtonItem
    -0.58
     part
    -0.57
    "/",
    -0.56
    POSITIVE LOGITS
     inteiro
    0.72
     verteilt
    0.59
    invokeLater
    0.55
     entière
    0.55
    WindowConstants
    0.52
    Enllaces
    0.52
    曖昧さ回避
    0.52
    DataPropertyName
    0.50
     כול
    0.49
    oneofs
    0.47
    Activations Density 0.585%

    No Known Activations