© 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. 9-GEMMASCOPE-RES-16K
    11. 918
    Prev
    Next
    INDEX
    Explanations

    questions and responses that convey uncertainty or requests for clarification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     فريبيس
    -1.05
     estekak
    -0.91
     protoimpl
    -0.78
    RTDA
    -0.77
     estimés
    -0.75
    atrième
    -0.74
    AccessorTable
    -0.74
     Walkover
    -0.73
    ngths
    -0.72
    virons
    -0.72
    POSITIVE LOGITS
    Do
    0.47
    ‘
    0.46
     venuto
    0.44
    Can
    0.42
    וֹ
    0.42
    Yeah
    0.42
    he
    0.41
    Indeed
    0.41
    門
    0.41
    He
    0.41
    Activations Density 0.133%

    No Known Activations