© 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. 31-GEMMASCOPE-RES-16K
    11. 10588
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to parenting experiences and emotions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    question-and-answer or interview format exchanges.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ſelves
    -0.66
     viſ
    -0.63
     HasFactory
    -0.63
     BoxFit
    -0.61
    出版年
    -0.57
     myſelf
    -0.57
     ſtate
    -0.57
     ſta
    -0.57
     purpoſe
    -0.56
     ſeveral
    -0.56
    POSITIVE LOGITS
     proudest
    0.81
     inspiração
    0.70
     inspiración
    0.66
     inspiration
    0.63
     inspirations
    0.61
     experience
    0.61
     toughest
    0.58
     favorite
    0.58
     highlights
    0.57
    苦労
    0.57
    Activations Density 0.217%

    No Known Activations