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. 22-GEMMASCOPE-MLP-16K
    6. 15784
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to the act of listening and its importance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-mlp-16k
    Configuration
    google/gemma-scope-2b-pt-mlp/layer_22/width_16k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_mlp_out
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Italijanski
    -0.63
    TypedDataSet
    -0.60
    rawDesc
    -0.57
    Carriera
    -0.55
     Ceinture
    -0.54
    uxxxx
    -0.53
    bentar
    -0.53
     để
    -0.53
    Дере
    -0.53
    XtraGrid
    -0.53
    POSITIVE LOGITS
     t
    0.92
     ta
    0.91
     top
    0.84
     ton
    0.76
     tu
    0.72
     td
    0.67
     TOP
    0.66
     tc
    0.64
     tp
    0.64
    top
    0.62
    Activations Density 1.589%

    No Known Activations