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. 6-GEMMASCOPE-RES-16K
    6. 2549
    Prev
    Next
    INDEX
    Explanations

    terms related to ice cream and dairy products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    httphttps
    -0.77
     AssemblyProduct
    -0.75
    esgue
    -0.74
    boxer
    -0.73
    }{|
    -0.71
    Petra
    -0.71
    hWnd
    -0.70
    kyou
    -0.68
    __*/
    -0.67
    AlterField
    -0.67
    POSITIVE LOGITS
     Cream
    1.65
     cream
    1.58
    Cream
    1.55
     CREAM
    1.49
    cream
    1.44
     creams
    1.24
     crema
    0.92
     creamy
    0.91
    creamy
    0.89
    クリーム
    0.89
    Activations Density 0.091%

    No Known Activations