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

    Neuronpedia

    APICircuit 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 - 65k
    5. 12-GEMMASCOPE-RES-65K
    6. 43397
    Prev
    Next
    INDEX
    Explanations

    phrases related to mobile optimization for websites

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aarrggbb
    -1.02
    ftagPool
    -0.84
    IVEREF
    -0.83
    httphttps
    -0.82
    parsedMessage
    -0.81
    ."]
    -0.80
    )");
    
    -0.80
    ]")]
    -0.77
     InputDecoration
    -0.77
     GlobalKey
    -0.76
    POSITIVE LOGITS
     mobile
    0.67
    mobile
    0.54
    Device
    0.52
     width
    0.52
     cellulare
    0.52
     Mobile
    0.51
     devices
    0.50
    Mobile
    0.49
     device
    0.46
    手机
    0.45
    Activations Density 0.026%

    No Known Activations