© 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. 37-GEMMASCOPE-RES-16K
    11. 1546
    Prev
    Next
    INDEX
    Explanations

    promotional language related to products and services

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     iirc
    -0.69
     bastante
    -0.63
     whatnot
    -0.62
    一応
    -0.62
    较为
    -0.61
     somewhat
    -0.59
    割と
    -0.57
    SerializeField
    -0.56
     InputDecoration
    -0.53
     ladite
    -0.53
    POSITIVE LOGITS
     unforgettable
    0.71
     effortlessly
    0.65
     effortless
    0.63
     smarter
    0.59
     confidently
    0.58
     unsurpassed
    0.58
     uncompromising
    0.58
     your
    0.56
     irresistible
    0.56
     unmistak
    0.56
    Activations Density 0.842%

    No Known Activations