© 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
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 14279
    Prev
    Next
    INDEX
    Explanations

    escape sequences and syntax related to programming or markup languages

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

    Characters that break URLs or code snippets

    np_acts-logits-general · gemini-2.0-flash

    regular expression syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    interopRequire
    -0.49
     Argentino
    -0.37
     arque
    -0.33
     ran
    -0.33
     run
    -0.32
     nahilalakip
    -0.32
     Serbs
    -0.32
    enumi
    -0.32
    roek
    -0.32
    jspx
    -0.31
    POSITIVE LOGITS
     EconPapers
    0.53
    
    0.48
     intStringLen
    0.46
     AssemblyVersion
    0.45
    CELLANEOUS
    0.45
    Hå
    0.44
     MotionEvent
    0.44
    moist
    0.44
    cheerful
    0.43
    elfde
    0.42
    Activations Density 0.627%

    No Known Activations