© 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-2-9B
    7. Residual Stream - 16k
    9. 27-GEMMASCOPE-RES-16K
    11. 10540
    Prev
    Next
    INDEX
    Explanations

    references to banking services and financial products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Seminar
    -0.60
     devin
    -0.57
     seminar
    -0.55
    Уважаемые
    -0.54
     &___
    -0.54
     Seminar
    -0.51
    Sinopse
    -0.50
    拼音
    -0.50
     noDo
    -0.48
    ronpa
    -0.48
    POSITIVE LOGITS
     непло
    0.48
     boasts
    0.44
     decently
    0.42
     impressively
    0.41
     excellent
    0.41
     excellently
    0.40
     khá
    0.39
     offers
    0.39
     impressive
    0.38
     decent
    0.38
    Activations Density 0.202%

    No Known Activations