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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. MLP Out - 131k
    9. 6-GEMMASCOPE-MLP-131K
    11. 109162
    Prev
    Next
    INDEX
    Explanations

    references to gastrointestinal topics or issues related to the digestive system

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-mlp/layer_6/width_131k/average_l0_72
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.6.hook_mlp_out
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     GI
    -1.84
    GI
    -1.55
     gi
    -0.94
     Gi
    -0.83
    Gi
    -0.82
    gi
    -0.69
     Giant
    -0.69
     للمعارف
    -0.67
    Giant
    -0.63
     disambiguazione
    -0.61
    POSITIVE LOGITS
     gan
    0.37
     Wagen
    0.37
    ῦ
    0.34
    ạng
    0.33
    ksikon
    0.33
    inheritDoc
    0.33
    aly
    0.33
    工
    0.33
     participating
    0.32
    ovo
    0.32
    Activations Density 0.003%

    No Known Activations