© 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. 110001
    Prev
    Next
    INDEX
    Explanations

    operations related to reading and writing files in code

    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
    writeFieldEnd
    -0.60
    RTEX
    -0.57
    PerformLayout
    -0.55
    uxxxx
    -0.54
    windowFixed
    -0.53
    exitRule
    -0.52
    addContainerGap
    -0.49
     Савезне
    -0.48
     Photocase
    -0.46
    StructEnd
    -0.45
    POSITIVE LOGITS
    mybatisplus
    0.49
     跳转至
    0.36
    Reilly
    0.36
    processable
    0.35
     Vend
    0.35
     مج
    0.35
     通販
    0.34
    auto
    0.34
    deka
    0.33
     ос
    0.33
    Activations Density 0.001%

    No Known Activations