© 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. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 105635
    Prev
    Next
    INDEX
    Explanations

    correlation and comparison expressions

    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
    SharedDtor
    -0.30
    可
    -0.30
     wolle
    -0.30
     far
    -0.30
    яр
    -0.29
     explic
    -0.28
     Ex
    -0.28
    합
    -0.28
    Ex
    -0.28
    EX
    -0.27
    POSITIVE LOGITS
     ujednoznacz
    0.77
     AssemblyCulture
    0.75
    principalColumn
    0.75
     AssemblyTitle
    0.73
    KURZBESCHREIBUNG
    0.72
    RegressionTest
    0.71
     nakalista
    0.71
    Autoritní
    0.69
    expandindo
    0.68
     estekak
    0.68
    Activations Density 0.062%

    No Known Activations