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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 2653
    Prev
    Next
    INDEX
    Explanations

    references to well-known songs and their artists, particularly in the context of soundtracks

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

    AP pelvis radiograph

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PerformLayout
    -0.63
    fjspx
    -0.57
    RegressionTest
    -0.52
     GoogleFonts
    -0.50
     ſind
    -0.47
    AndEndTag
    -0.47
    deleteById
    -0.46
    liceerd
    -0.46
    setupUi
    -0.45
    ThroughAttribute
    -0.45
    POSITIVE LOGITS
     EconPapers
    0.40
    ManagedBean
    0.36
     Jagger
    0.34
    iarkan
    0.34
     rolling
    0.33
     Rolling
    0.33
     tumb
    0.33
     rolled
    0.32
    NamedQueries
    0.32
     DIGITAL
    0.31
    Activations Density 0.087%

    No Known Activations