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. 0-GEMMASCOPE-MLP-65K
    6. 61072
    Prev
    Next
    INDEX
    Explanations

    references to debit cards and their usage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-mlp-65k
    Configuration
    google/gemma-scope-2b-pt-mlp/layer_0/width_65k/average_l0_72
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.0.hook_mlp_out
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ddelweddau
    -1.01
    esine
    -0.85
    RegressionTest
    -0.85
     Italijanski
    -0.84
     leksikon
    -0.77
    Reducers
    -0.77
    GeneratedCode
    -0.76
    WireFormat
    -0.75
     Wiktionnaire
    -0.73
     Soviets
    -0.73
    POSITIVE LOGITS
    theless
    0.75
    følgelig
    0.70
    zitter
    0.62
    hidupan
    0.61
    ckså
    0.60
    ization
    0.59
    adays
    0.58
    ceutical
    0.56
    withstanding
    0.53
    Literatuur
    0.53
    Activations Density 0.017%

    No Known Activations