© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 2888
    Prev
    Next
    INDEX
    Explanations

    narrative elements related to customer service and interpersonal interactions

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    the word "heard" and associated auditory perception verbs and moments.

    oai_token-act-pair · claude-4-5-haiku
    Triggered 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
    Negative Logits
     természetes
    -0.32
     paciencia
    -0.32
     intérieure
    -0.32
     srdce
    -0.30
     rzeczyw
    -0.30
     ulang
    -0.29
    当场
    -0.29
     razem
    -0.28
     triunfo
    -0.28
     dziel
    -0.28
    POSITIVE LOGITS
     familiar
    0.88
     voices
    0.84
     strange
    0.80
     unfamiliar
    0.77
     noises
    0.77
     voice
    0.74
     anomaly
    0.73
     mysterious
    0.73
    familiar
    0.73
     figures
    0.71
    Activations Density 0.299%

    No Known Activations