© 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. 109330
    Prev
    Next
    INDEX
    Explanations

    mentions of variable names and their descriptions

    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
     name
    -0.91
     names
    -0.82
     NAME
    -0.68
    名称
    -0.66
     Names
    -0.65
     Name
    -0.63
     Namen
    -0.63
     nomes
    -0.63
    名前
    -0.62
    的名字
    -0.62
    POSITIVE LOGITS
    featureID
    0.41
     Factbook
    0.39
    IActionResult
    0.39
     насељу
    0.38
     betweenstory
    0.38
    chartInstance
    0.38
     onCancelled
    0.37
     Bias
    0.37
    endphp
    0.36
     članak
    0.36
    Activations Density 0.016%

    No Known Activations