© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 104322
    Prev
    Next
    INDEX
    Explanations

    operations involving string concatenation and message appending

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     myſelf
    -0.78
     invokingState
    -0.73
    TypedDataSet
    -0.72
     snippetHide
    -0.70
    adaptiveStyles
    -0.69
     للاسماء
    -0.69
     <>",
    -0.68
    ंदीखरीदारी
    -0.66
     ſta
    -0.65
    MigrationBuilder
    -0.63
    POSITIVE LOGITS
     +=
    0.51
    WriteString
    0.44
     .=
    0.41
    +=
    0.39
    AppendLine
    0.38
     terjadinya
    0.37
     terecht
    0.36
    +="
    0.35
    OTS
    0.34
     идет
    0.34
    Activations Density 0.009%

    No Known Activations