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. 15751
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "come" and its variations

    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
     مشين
    -0.67
     محفوظة
    -0.54
    MENAFN
    -0.54
     nonatomic
    -0.53
    SpringRunner
    -0.52
     pick
    -0.50
     Процитовано
    -0.49
     Wat
    -0.49
    grá
    -0.49
     EClass
    -0.47
    POSITIVE LOGITS
    Географиясе
    0.64
     gawas
    0.59
    لينكات
    0.57
    offsetof
    0.54
     <<<<<<<<<<<<<<
    0.54
     TID
    0.53
    клопе
    0.52
    issements
    0.51
    Опис
    0.51
    );?>
    0.50
    Activations Density 0.084%

    No Known Activations