© 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. 109106
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "verse" and its variations within textual data

    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
    verse
    -2.03
    Verse
    -1.41
    VERSE
    -1.33
     verse
    -1.20
     Verse
    -1.15
    verses
    -1.03
    verso
    -0.81
    Verses
    -0.76
     verses
    -0.73
    versa
    -0.68
    POSITIVE LOGITS
     noDo
    0.63
     архивлан
    0.62
    IndentedString
    0.60
     @"/
    0.58
    RegressionTest
    0.57
    TRAILING
    0.56
     tartalomajánló
    0.54
    ThemeOverlay
    0.54
     لينك
    0.54
    elemField
    0.54
    Activations Density 0.001%

    No Known Activations