© 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. 36-GEMMASCOPE-RES-16K
    11. 14618
    Prev
    Next
    INDEX
    Explanations

    references to authority figures and hierarchical structures in a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     surla
    -0.84
     nakalista
    -0.78
    MessageOf
    -0.73
    AsUp
    -0.64
    省市镇
    -0.63
     otomatig
    -0.61
     autorytatywna
    -0.61
    Ծանոթ
    -0.59
     sorts
    -0.58
    luents
    -0.58
    POSITIVE LOGITS
     opponent
    0.47
    +#+#
    0.34
     investis
    0.32
     originally
    0.30
     démocr
    0.29
     whole
    0.29
     springfox
    0.28
     crowd
    0.28
    เศ
    0.28
     ?>/
    0.28
    Activations Density 0.088%

    No Known Activations