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. 15-GEMMASCOPE-RES-16K
    6. 5316
    Prev
    Next
    INDEX
    Explanations

    references to mobile devices and applications

    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
     الحره
    -0.60
    例文帳に追加
    -0.56
     Melch
    -0.54
    ftagPool
    -0.52
    astify
    -0.52
     AssemblyProduct
    -0.52
    存于互联网档案馆
    -0.50
    Amicalement
    -0.50
     Mellon
    -0.50
     Salgado
    -0.49
    POSITIVE LOGITS
     phones
    1.18
     smartphone
    1.12
     Android
    1.10
     phone
    1.08
     smartphones
    1.07
     Smartphone
    0.98
     Smartphones
    0.97
    smartphone
    0.96
     iPhone
    0.95
     mobile
    0.95
    Activations Density 0.373%

    No Known Activations