© 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. 11353
    Prev
    Next
    INDEX
    Explanations

    sentences reflecting personal childhood memories and experiences

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

    nostalgic personal memories of childhood and past decades.

    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
     derzeit
    -0.61
     momentan
    -0.56
     currently
    -0.56
    目前
    -0.54
     recent
    -0.51
     Currently
    -0.49
    Currently
    -0.48
    recent
    -0.48
     obecnie
    -0.47
     actuellement
    -0.47
    POSITIVE LOGITS
    那时候
    1.03
     damals
    0.99
    当時は
    0.95
    当時
    0.89
    当時の
    0.89
    那时
    0.85
     помню
    0.83
    当时的
    0.81
    當時
    0.80
     damal
    0.79
    Activations Density 0.530%

    No Known Activations