© 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. 110012
    Prev
    Next
    INDEX
    Explanations

    references to the reader or the self in context

    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
    Sklici
    -0.52
    AsUp
    -0.52
     preocupación
    -0.50
    RegressionTest
    -0.49
    JoinTable
    -0.49
     sobie
    -0.49
    хьтан
    -0.48
     transición
    -0.48
     mijne
    -0.48
     consideración
    -0.47
    POSITIVE LOGITS
    setVerticalGroup
    0.54
     larg
    0.41
    向
    0.37
     GM
    0.36
     laid
    0.36
    frag
    0.35
    حة
    0.35
     giant
    0.35
     bent
    0.34
     fre
    0.34
    Activations Density 0.005%

    No Known Activations