© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 1352
    Prev
    Next
    INDEX
    Explanations

    terms related to property listings and legal disclaimers

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

    details related to residential property specifications

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

    legal terms and disclaimers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    modificar
    -0.51
    ilea
    -0.50
     بلکه
    -0.50
    ższych
    -0.49
    Ưu
    -0.48
    WriteBarrier
    -0.48
    leda
    -0.46
    ']?>
    -0.46
     initComponents
    -0.46
    válasz
    -0.45
    POSITIVE LOGITS
    MessageTagHelper
    0.77
    PerformLayout
    0.67
    Salta
    0.55
     ($)
    0.54
     linkovi
    0.53
    ViewFeatures
    0.52
     Schot
    0.50
    UserScript
    0.50
     NUKAT
    0.50
    rateur
    0.50
    Activations Density 0.015%

    No Known Activations