© 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. 2198
    Prev
    Next
    INDEX
    Explanations

    programming terms associated with user interface layout

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    Activités
    -1.63
    Activité
    -1.34
    Попис
    -0.62
     مشين
    -0.59
    GeneratedMessage
    -0.58
    activity
    -0.57
     ACTIVITY
    -0.56
     activity
    -0.54
    principalColumn
    -0.54
    Hozzáférés
    -0.52
    POSITIVE LOGITS
    DockStyle
    3.09
    complexContent
    2.53
    Erstellt
    2.20
    currentColor
    1.84
    WithMany
    1.33
    出版年
    0.89
    Życiorys
    0.80
    SequentialGroup
    0.79
     تضيفلها
    0.79
    oredCriteria
    0.79
    Activations Density 0.000%

    No Known Activations