© 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. 574
    Prev
    Next
    INDEX
    Explanations

    references to various types of bread and bread-related dishes

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

    ingredients and details related to breads and sandwiches.

    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
    TagMode
    -0.50
     especta
    -0.49
    AndEndTag
    -0.48
     kasarigan
    -0.47
     للاسماء
    -0.46
    Ծանոթ
    -0.46
     Lingkungan
    -0.45
    RTGC
    -0.44
     Achter
    -0.43
    piscina
    -0.42
    POSITIVE LOGITS
     bread
    0.78
     Bread
    0.76
     loaves
    0.74
     bakery
    0.74
     baked
    0.72
     loaf
    0.68
     breads
    0.68
     Loaf
    0.65
    bread
    0.65
    Bread
    0.60
    Activations Density 0.098%

    No Known Activations