© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 9767
    Prev
    Next
    INDEX
    Explanations

    medical-related actions and situations involving personnel

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

    sports-related training, practice, and professional activities.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     hidupnya
    -0.46
    Notae
    -0.44
    󠁣
    -0.43
    LabelTagHelper
    -0.42
     ícones
    -0.40
     inimes
    -0.40
     uživ
    -0.40
    rungsseite
    -0.40
     cuchar
    -0.40
     Umständen
    -0.38
    POSITIVE LOGITS
     training
    0.72
     Training
    0.63
     drills
    0.63
     workouts
    0.63
     PRACTICE
    0.61
    training
    0.61
     latihan
    0.61
     تمرین
    0.60
     practice
    0.60
    練習
    0.59
    Activations Density 0.067%

    No Known Activations