© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 31014
    Prev
    Next
    INDEX
    Explanations

    references to information handling and technology systems

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

    information technology and systems

    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
     Comprometido
    -0.62
    cuer
    -0.55
     prz
    -0.47
    OVERR
    -0.47
     scorso
    -0.47
     Erwartungen
    -0.46
    Oleh
    -0.45
    équi
    -0.44
     Geschle
    -0.44
    Muy
    -0.44
    POSITIVE LOGITS
     Information
    1.05
     information
    1.04
    Information
    0.93
    information
    0.91
     informations
    0.86
     INFORMATION
    0.84
     informational
    0.81
    INFORMATION
    0.80
     Info
    0.73
    informations
    0.73
    Activations Density 0.015%

    No Known Activations