© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 105971
    Prev
    Next
    INDEX
    Explanations

    numerical patterns and values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
    transQ
    -0.50
    UnifiedTopology
    -0.50
     թվական
    -0.46
     Autorizaciones
    -0.45
    mobileqq
    -0.45
     فريبيس
    -0.45
     BoxDecoration
    -0.45
     mauva
    -0.45
    jspb
    -0.44
    HasAnnotation
    -0.43
    POSITIVE LOGITS
     للمعارف
    0.52
    олові
    0.52
     <<<<<<<<<<<<<<
    0.45
    EndInit
    0.41
     darken
    0.39
    istoitu
    0.39
    archiviato
    0.39
    ToRefresh
    0.38
    bidi
    0.37
     wirk
    0.37
    Activations Density 0.146%

    No Known Activations