© 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. 11-GEMMASCOPE-RES-16K
    11. 5092
    Prev
    Next
    INDEX
    Explanations

    sentences that express a sense of urgency or personal reflection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/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.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mergeFrom
    -0.57
     kasarigan
    -0.55
    Hentet
    -0.54
     snippetHide
    -0.53
    OGND
    -0.53
    Autoritní
    -0.53
     فريبيس
    -0.52
    InteropServices
    -0.48
    itinéraire
    -0.47
    iffance
    -0.45
    POSITIVE LOGITS
     ‘
    0.47
    …’
    0.45
    ’:
    0.42
    🏻‍♀️
    0.42
    ‘
    0.40
    🏻
    0.40
    ˾
    0.39
    ‍♂️
    0.38
     defStyleAttr
    0.38
    出版年
    0.38
    Activations Density 1.656%

    No Known Activations