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. 8861
    Prev
    Next
    INDEX
    Explanations

    terms related to establishing connections in communication protocols

    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
    connect
    -1.30
     connect
    -1.30
    Connect
    -1.29
     Connect
    -1.27
     connecting
    -1.10
    Connecting
    -1.07
    Connection
    -1.07
     CONNECT
    -1.06
    CONNECT
    -1.04
     Connecting
    -1.03
    POSITIVE LOGITS
    SourceChecksum
    0.79
    TagMode
    0.75
    ParallelGroup
    0.73
    AddTagHelper
    0.66
    ThroughAttribute
    0.64
    tamol
    0.62
    ItemBackground
    0.61
    ignez
    0.58
    WithIOException
    0.57
    sizeCache
    0.56
    Activations Density 0.304%

    No Known Activations