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. 15801
    Prev
    Next
    INDEX
    Explanations

    links and references to external stylesheets in HTML code

    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
     kasarigan
    -0.79
    WARDS
    -0.69
     تضيفلها
    -0.65
    Chham
    -0.62
    RUnlock
    -0.61
    WARD
    -0.58
     оригіналу
    -0.56
    HasAnnotation
    -0.56
     Италијани
    -0.56
     APPRO
    -0.55
    POSITIVE LOGITS
    tilhe
    0.55
     rel
    0.51
    readAs
    0.50
    ="@+
    0.48
     africaine
    0.47
     beginnetje
    0.47
    ErrorListener
    0.46
    ftagPool
    0.45
    __(/*!
    0.43
     pinulongan
    0.43
    Activations Density 0.028%

    No Known Activations