© 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. 3838
    Prev
    Next
    INDEX
    Explanations

    emotional responses related to loss and the effects of tragedy

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

    expressions of emotional distress, grief, and intense personal suffering.

    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
    有趣
    -0.54
    有趣的
    -0.49
    嘿嘿
    -0.49
     ;)
    -0.47
     😉
    -0.47
     advantageous
    -0.45
     interesante
    -0.45
     Interesting
    -0.44
     complain
    -0.44
     😎
    -0.44
    POSITIVE LOGITS
     heartbreaking
    1.17
     heartbreak
    1.05
     horrifying
    1.01
     horrific
    0.96
     harrowing
    0.91
     terrifying
    0.90
     devastation
    0.90
     devastating
    0.90
     heartbroken
    0.89
     anguish
    0.88
    Activations Density 0.418%

    No Known Activations