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

    statements indicating suspicion or an indication that something might be wrong

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-mlp-16k
    Configuration
    google/gemma-scope-2b-pt-mlp/layer_6/width_16k/average_l0_133
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_mlp_out
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     חיצוניים
    -0.87
    Климат
    -0.62
     knex
    -0.61
     ModelExpression
    -0.60
     something
    -0.60
    totic
    -0.58
     Département
    -0.56
    些什么
    -0.56
    GetAsync
    -0.56
    chengladbach
    -0.56
    POSITIVE LOGITS
    SequentialGroup
    0.59
     transférez
    0.57
     BorderRadius
    0.54
    WithEmail
    0.52
     vedea
    0.50
     JADX
    0.45
     Patriarch
    0.42
    >');
    0.42
    \]
    0.42
    UseVisualStyle
    0.42
    Activations Density 0.284%

    No Known Activations