© 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. 62694
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    InputBorder
    -0.59
    
    -0.53
    medriver
    -0.52
    hObject
    -0.52
    wapV
    -0.51
     мәкал
    -0.50
    userManager
    -0.50
    GenerationType
    -0.49
    kloped
    -0.49
    ochim
    -0.48
    POSITIVE LOGITS
    ViewFeatures
    1.89
    
    0.39
     للاسماء
    0.38
    .*")]
    0.38
     addSubview
    0.37
    CppMethod
    0.37
    Personensuche
    0.36
     pourtant
    0.36
    IUrlHelper
    0.36
    ScopeManager
    0.35
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.