© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 8993
    Prev
    Next
    INDEX
    Explanations

    references to brushes and their related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     censiti
    -0.50
    cipit
    -0.44
     gewiß
    -0.43
     lohnt
    -0.43
    Гео
    -0.42
     setId
    -0.42
    delwed
    -0.41
    
    -0.41
    çalves
    -0.40
     Foire
    -0.40
    POSITIVE LOGITS
     Bush
    0.90
    Bush
    0.87
     Wayne
    0.87
    Wayne
    0.82
     Bruce
    0.82
     bush
    0.80
     Trump
    0.79
    Bruce
    0.77
     Brush
    0.77
    Trump
    0.75
    Activations Density 0.122%

    No Known Activations