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. 15778
    Prev
    Next
    INDEX
    Explanations

    references to privacy and data protection

    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
    XmlAccessorType
    -0.59
    Morfologia
    -0.43
    Citation
    -0.42
     stránka
    -0.42
    styleUrls
    -0.42
    domino
    -0.40
     OkHttpClient
    -0.40
     Gson
    -0.40
    DataSnapshot
    -0.39
    pes
    -0.39
    POSITIVE LOGITS
     EconPapers
    0.78
     تضيفلها
    0.74
     تانيه
    0.74
     ExecuteAsync
    0.74
    الحياه
    0.68
    AddAttribute
    0.67
    
    0.66
    MigrationBuilder
    0.65
     autorytatywna
    0.65
    __':
    
    0.64
    Activations Density 1.624%

    No Known Activations