© 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. 20-GEMMASCOPE-RES-131K
    11. 44435
    Prev
    Next
    INDEX
    Explanations

    sequences of whitespace or indentation characters in code

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

    code keywords

    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
     propOrder
    -0.95
    WebElementEntity
    -0.93
    
    -0.92
    sizeCache
    -0.91
    +#+
    -0.88
     ProtoMessage
    -0.88
    Personendaten
    -0.86
    oredCriteria
    -0.84
    +#+#
    -0.81
    setupUi
    -0.80
    POSITIVE LOGITS
    1
    0.37
    FR
    0.36
    2
    0.35
    How
    0.34
    I
    0.34
     Mit
    0.34
    Profile
    0.33
    ，
    0.33
    ală
    0.33
    ’
    0.33
    Activations Density 0.004%

    No Known Activations