Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. MLP Out - 131k
    5. 6-GEMMASCOPE-MLP-131K
    6. 109688
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "使用," which means "to use."

    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
    使用
    -1.21
     使用
    -0.87
     사용
    -0.64
    的使用
    -0.63
    使用了
    -0.60
    可以使用
    -0.60
    使用的
    -0.58
    使用する
    -0.57
    EndContext
    -0.56
    使用方法
    -0.56
    POSITIVE LOGITS
    Билгалдахарш
    0.51
     auroit
    0.47
     avoient
    0.45
     étoient
    0.45
     étoit
    0.45
     feroit
    0.44
     llegará
    0.40
     inscrição
    0.39
    zbęd
    0.39
     plomo
    0.38
    Activations Density 0.001%

    No Known Activations