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. MLP Out - 65k
    5. 0-GEMMASCOPE-MLP-65K
    6. 60960
    Prev
    Next
    INDEX
    Explanations

    the presence of a specific sequence of characters related to a name, likely connected to an author or researcher

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-mlp-65k
    Configuration
    google/gemma-scope-2b-pt-mlp/layer_0/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.0.hook_mlp_out
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IsContent
    -0.79
     initComponents
    -0.77
    __':
    -0.74
    +#+#
    -0.73
     ArrayAdapter
    -0.72
    zahn
    -0.71
    DoubleQuotes
    -0.70
     ویکی‌آمباردا
    -0.69
    thage
    -0.67
     AssemblyTitle
    -0.67
    POSITIVE LOGITS
     ſever
    0.94
    neſs
    0.88
     faſt
    0.81
     myſelf
    0.81
     ſche
    0.79
     iſt
    0.78
    ſelves
    0.78
     juſ
    0.77
     noft
    0.77
     ſta
    0.77
    Activations Density 0.004%

    No Known Activations