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 - 65k
    5. 4-GEMMASCOPE-MLP-65K
    6. 49
    Prev
    Next
    INDEX
    Explanations

    terms related to object-oriented programming, particularly concerning prototypes and inheritance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-mlp-65k
    Configuration
    google/gemma-scope-2b-pt-mlp/layer_4/width_65k/average_l0_66
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.4.hook_mlp_out
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للمعارف
    -0.68
    GeoNames
    -0.61
     الدولى
    -0.58
     وتسجيلات
    -0.57
    hers
    -0.57
     asalto
    -0.55
     वाला
    -0.55
     useRouter
    -0.55
    enumi
    -0.54
     tér
    -0.54
    POSITIVE LOGITS
     disambiguazione
    0.65
    Datuak
    0.61
    ).]
    0.56
    ."]
    0.56
    .)}
    0.56
    IntoConstraints
    0.55
     }}"></
    0.52
    AndEndTag
    0.52
    )");
    
    0.52
    MessageOf
    0.51
    Activations Density 0.005%

    No Known Activations