© 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. 126943
    Prev
    Next
    INDEX
    Explanations

    CSS and JavaScript properties related to layout and positioning

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

    rails moving and scrolling

    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
    CloseOperation
    -0.65
    MigrationBuilder
    -0.59
    DockStyle
    -0.55
    AndEndTag
    -0.55
    featureID
    -0.54
     dévelo
    -0.54
    MLLoader
    -0.53
    BeginInit
    -0.52
    getDescriptor
    -0.49
     linkovi
    -0.49
    POSITIVE LOGITS
     Spots
    0.35
    łuż
    0.34
     menacing
    0.34
     replenish
    0.33
     retreating
    0.32
     drehen
    0.32
     lowering
    0.32
     personalizar
    0.32
     Einsch
    0.32
     damaging
    0.31
    Activations Density 0.005%

    No Known Activations