© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 8612
    Prev
    Next
    INDEX
    Explanations

    culinary actions and ingredients in recipes

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

    Preceding words "Add", "and", "Party", "our", or "."

    np_acts-logits-general · gemini-2.0-flash

    Add, and, party, our, of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ujednoznacz
    -0.55
    stand
    -0.50
    koli
    -0.48
     bağlantılar
    -0.48
    Subclass
    -0.48
     duquel
    -0.48
    存于互联网档案馆
    -0.46
    wts
    -0.46
    典型
    -0.46
     remercie
    -0.46
    POSITIVE LOGITS
    Personendaten
    0.83
    iibo
    0.74
    zmir
    0.58
     half
    0.52
    олові
    0.50
    
    0.50
     kasarigan
    0.50
    enterOuterAlt
    0.49
    MessageOf
    0.49
    piratory
    0.49
    Activations Density 0.176%

    No Known Activations