© 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. 110194
    Prev
    Next
    INDEX
    Explanations

    references to the concept of leaving or departure

    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
     leave
    -1.33
     Leave
    -1.13
    leave
    -1.09
    Leave
    -1.09
     LEAVE
    -1.04
     leaves
    -0.91
     leaving
    -0.90
    LEAVE
    -0.81
     meninggalkan
    -0.75
     оставить
    -0.75
    POSITIVE LOGITS
     <=",
    0.64
    enumii
    0.58
    QMetaType
    0.57
    LabelTagHelper
    0.57
     surla
    0.56
    UnitTesting
    0.52
     Taktlose
    0.51
    oredCriteria
    0.51
    findpost
    0.50
    parsedMessage
    0.50
    Activations Density 0.007%

    No Known Activations