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 - 16k
    5. 1-GEMMASCOPE-MLP-16K
    6. 8771
    Prev
    Next
    INDEX
    Explanations

    terms related to seasonal changes and time periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-mlp-16k
    Configuration
    google/gemma-scope-2b-pt-mlp/layer_1/width_16k/average_l0_105
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_mlp_out
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    '])->
    -0.50
    >';
    
    -0.50
    Aholisi
    -0.49
    '`
    -0.47
    ')))
    -0.44
    )}+
    -0.43
    ')));
    -0.43
    '))
    
    -0.43
     registration
    -0.43
    /'.$
    -0.42
    POSITIVE LOGITS
    存于互联网档案馆
    0.77
    IUrlHelper
    0.75
    makeConstraints
    0.75
     Italijanski
    0.74
    AddTagHelper
    0.72
    ThroughAttribute
    0.71
    \{\\
    0.68
     препратки
    0.67
    InvalidProtocol
    0.67
    __(/*!
    0.66
    Activations Density 0.688%

    No Known Activations