© 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. 10-GEMMASCOPE-RES-16K
    11. 12654
    Prev
    Next
    INDEX
    Explanations

    inquiries and questions related to support and clarification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     itſelf
    -0.60
    CrossRef
    -0.57
     metav
    -0.56
    Personensuche
    -0.55
    EDEFAULT
    -0.54
     queſta
    -0.53
    makeConstraints
    -0.52
    OGND
    -0.52
    ViewImports
    -0.52
    səhifə
    -0.52
    POSITIVE LOGITS
     answers
    0.70
     FAQ
    0.70
     FAQs
    0.66
     questions
    0.65
     answering
    0.59
    FAQ
    0.59
     Questions
    0.59
     answered
    0.58
    answers
    0.57
     dúvidas
    0.57
    Activations Density 0.396%

    No Known Activations