© 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. 8191
    Prev
    Next
    INDEX
    Explanations

    instances of the word 'excellent'

    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
     fandom
    -0.49
     bunnies
    -0.49
     Skincare
    -0.48
     naive
    -0.47
    Liefs
    -0.45
     crashing
    -0.45
     bunny
    -0.45
     sayin
    -0.43
     magically
    -0.43
    йлер
    -0.42
    POSITIVE LOGITS
     excellent
    3.25
    excellent
    3.11
    Excellent
    3.02
     Excellent
    2.94
     EXCELL
    2.41
     excelente
    2.33
     excellente
    2.23
     excelentes
    2.19
    excelente
    1.98
     excellence
    1.97
    Activations Density 0.044%

    No Known Activations