© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 87814
    Prev
    Next
    INDEX
    Explanations

    lines of code or programming constructs associated with object manipulation and method calls

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

    programming variable assignment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    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
     betweenstory
    -0.73
    transQ
    -0.69
    الحياه
    -0.68
    ValueStyle
    -0.65
     Chwiliwch
    -0.65
     propOrder
    -0.63
    GHIJKLM
    -0.61
     CreateTagHelper
    -0.61
    IntoConstraints
    -0.60
     Photocase
    -0.59
    POSITIVE LOGITS
     hany
    0.38
    Wirtschaft
    0.37
    ्टी
    0.37
     INSTITUTION
    0.36
     est
    0.34
     edited
    0.34
    mphony
    0.34
    menu
    0.34
     edit
    0.33
    जी
    0.33
    Activations Density 0.031%

    No Known Activations