© 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. 3644
    Prev
    Next
    INDEX
    Explanations

    references to personal experiences or emotions in relationships

    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
    adpleegd
    -0.47
    出版年
    -0.46
    Espèce
    -0.46
     lenker
    -0.46
    portál
    -0.45
     Réponses
    -0.44
     Brno
    -0.43
     protoimpl
    -0.42
    AndEndTag
    -0.42
    Aussie
    -0.42
    POSITIVE LOGITS
    🏾
    1.16
     niggas
    0.83
     nigga
    0.79
    🏽
    0.75
     smh
    0.74
    🏿
    0.69
     hella
    0.64
     tryna
    0.62
     dope
    0.61
     Jamaican
    0.61
    Activations Density 0.473%

    No Known Activations