© 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. 9-GEMMASCOPE-RES-131K
    11. 94773
    Prev
    Next
    INDEX
    Explanations

    programming-related syntax and structure elements, particularly focusing on enclosures and formatting in code

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

    enclosed in brackets or quotes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     propOrder
    -0.61
    twimg
    -0.60
     otomatig
    -0.59
     Autorisations
    -0.59
     jsPsych
    -0.58
     Autorizaciones
    -0.57
    RTGC
    -0.55
    RTEX
    -0.55
    mbic
    -0.54
    :✨
    -0.52
    POSITIVE LOGITS
    CloseOperation
    0.37
    uspiel
    0.33
     surrounded
    0.32
     reproducción
    0.32
     Vane
    0.31
    ioutil
    0.31
    OutputType
    0.31
     surrounding
    0.31
     pôr
    0.31
     chunks
    0.30
    Activations Density 0.284%

    No Known Activations