© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. MLP Out - 16k
    9. 19-GEMMASCOPE-MLP-16K
    11. 9543
    Prev
    Next
    INDEX
    Explanations

    names and versions related to software or applications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-mlp-16k
    Configuration
    google/gemma-scope-2b-pt-mlp/layer_19/width_16k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_mlp_out
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     positive
    -1.15
    positive
    -1.05
     Positive
    -1.03
    Positive
    -1.00
     POSITIVE
    -0.99
     positif
    -0.98
    >
    -0.94
     >
    -0.93
    )>
    -0.90
     positivas
    -0.88
    POSITIVE LOGITS
     ویکی‌پدیای
    0.68
    χρι
    0.65
    sizeCache
    0.61
    makeText
    0.58
    LabelTagHelper
    0.56
    RegressionTest
    0.56
    InputBorder
    0.54
    下载附件
    0.54
     صوتيه
    0.54
    ActionCreators
    0.52
    Activations Density 1.134%

    No Known Activations