© 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. 109274
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     setOpen
    -0.44
     CanadaChoose
    -0.42
     Geburt
    -0.38
     AttributeSet
    -0.38
    GeneratedMessage
    -0.35
     vaksinasi
    -0.35
     escote
    -0.35
     Fähigkeit
    -0.34
    
    -0.33
    berdayakan
    -0.33
    POSITIVE LOGITS
     تضيفلها
    0.58
    ECONDS
    0.52
    esez
    0.51
    rmtree
    0.50
    objPHPExcel
    0.45
    nteral
    0.41
    {#
    0.41
     comple
    0.41
    WithType
    0.40
    braio
    0.40
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.