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. 8750
    Prev
    Next
    INDEX
    Explanations

    technical terms related to image processing and analysis

    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
    商品説明
    -0.56
     ویکی‌پدیای
    -0.50
    Jap
    -0.50
     polskiego
    -0.48
     Jap
    -0.47
    udah
    -0.46
     camber
    -0.43
    っぱ
    -0.42
     tayo
    -0.41
    photos
    -0.40
    POSITIVE LOGITS
    >--}}
    0.69
    ">—
    0.65
    ThroughAttribute
    0.65
    __':
    0.62
    abend
    0.60
    ministrazione
    0.58
    usiai
    0.57
    Geplaatst
    0.56
    findpost
    0.56
    //
    0.56
    Activations Density 0.349%

    No Known Activations