© 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. 24-GEMMASCOPE-RES-131K
    11. 110
    Prev
    Next
    INDEX
    Explanations

    attributes and properties within code snippets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    code identifiers, titles, or filenames

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vania
    -0.35
    tim
    -0.34
     nor
    -0.32
    igkeit
    -0.32
     threshold
    -0.32
     مر
    -0.32
    ff
    -0.31
     conceivable
    -0.31
     possible
    -0.30
     next
    -0.30
    POSITIVE LOGITS
     незавершена
    0.81
     AssemblyTitle
    0.75
    RegressionTest
    0.70
     autorytatywna
    0.69
    TypedDataSet
    0.69
    Хьажоргаш
    0.68
    queryInterface
    0.68
    richTextPanel
    0.67
    enumi
    0.66
    Geplaatst
    0.66
    Activations Density 0.001%

    No Known Activations