© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. MLP Out - 131k
    5. 6-GEMMASCOPE-MLP-131K
    6. 110082
    Prev
    Next
    INDEX
    Explanations

    words related to accounting and reporting

    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
     EconPapers
    -0.48
    Crown
    -0.36
     insuffisamment
    -0.36
    felde
    -0.35
     rústico
    -0.34
    ✨:
    -0.34
    서는
    -0.34
     pust
    -0.33
    isMethod
    -0.33
     vintage
    -0.33
    POSITIVE LOGITS
     reporting
    0.88
     reported
    0.85
     Reporting
    0.79
    reported
    0.78
     report
    0.78
     REPORTING
    0.78
    reporting
    0.77
     Reported
    0.76
    Reporting
    0.75
    report
    0.70
    Activations Density 0.120%

    No Known Activations