© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 5520
    Prev
    Next
    INDEX
    Explanations

    expressions related to emotional and psychological struggles in the context of parenting and interpersonal challenges

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

    expressions describing emotional or physical strain and exhaustion.

    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
     للمعارف
    -0.40
     excitedly
    -0.36
     orta
    -0.35
    excited
    -0.33
     memu
    -0.33
    intahan
    -0.33
     recue
    -0.32
    Excited
    -0.32
    Linki
    -0.31
     excited
    -0.31
    POSITIVE LOGITS
     toll
    1.23
    toll
    0.90
     tolls
    0.90
     Toll
    0.82
    Toll
    0.82
     strain
    0.79
     strains
    0.71
     wear
    0.71
     drain
    0.68
     Strain
    0.68
    Activations Density 0.221%

    No Known Activations