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. 1-GEMMASCOPE-MLP-16K
    6. 8721
    Prev
    Next
    INDEX
    Explanations

    chemical formulas and compounds

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-mlp-16k
    Configuration
    google/gemma-scope-2b-pt-mlp/layer_1/width_16k/average_l0_105
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_mlp_out
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Siehe
    -0.44
    躇
    -0.43
    άλ
    -0.42
    ultar
    -0.42
    ರೆ
    -0.41
    setSource
    -0.41
    ấm
    -0.40
     yourself
    -0.40
    gaged
    -0.40
    مند
    -0.39
    POSITIVE LOGITS
    脚注の使い方
    0.88
    mybatisplus
    0.77
     للمعارف
    0.74
    Portale
    0.68
     StatefulWidget
    0.68
    曖昧さ回避
    0.66
    NameInMap
    0.62
    yargs
    0.62
    InstrumentedTest
    0.62
    AccessorTable
    0.61
    Activations Density 0.588%

    No Known Activations