© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 1087
    Prev
    Next
    INDEX
    Explanations

    references to ceremonies and memorials related to death and remembrance

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

    ceremonial or commemorative events like weddings, memorials, and graduations.

    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
     Hofmann
    -0.41
     fighting
    -0.38
     fresh
    -0.37
     Christensen
    -0.37
    ற்று
    -0.37
     underrated
    -0.36
    queles
    -0.36
    Filmografie
    -0.36
    ที่
    -0.34
     poisoning
    -0.34
    POSITIVE LOGITS
    CloseOperation
    0.59
     Италијани
    0.56
     tartalomajánló
    0.55
    twimg
    0.51
    httphttps
    0.51
    RenderAtEndOf
    0.50
     doInBackground
    0.50
    出版年
    0.49
    RTHOOK
    0.49
    FunctionFlags
    0.48
    Activations Density 0.011%

    No Known Activations