© 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. 9530
    Prev
    Next
    INDEX
    Explanations

    references to changes or developments in environmental policies and practices

    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
     was
    -1.54
    was
    -1.18
     wasn
    -1.16
     consisted
    -1.16
    Was
    -1.14
     seemed
    -1.13
     differed
    -1.13
     Was
    -1.13
     had
    -1.12
     existed
    -1.12
    POSITIVE LOGITS
    ]--;
    0.58
     are
    0.57
    chyma
    0.54
     następu
    0.50
    DeleteBehavior
    0.49
    われます
    0.49
    ofire
    0.49
    nosaurus
    0.48
     fazem
    0.48
     חיצוניים
    0.47
    Activations Density 2.263%

    No Known Activations