© 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. 13323
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to machine learning and emotion recognition

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

    technical code and configuration related to machine learning, data processing, and software development.

    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
     intercamb
    -0.34
     تو
    -0.31
     szár
    -0.31
     Instrumente
    -0.30
     inşa
    -0.29
     divul
    -0.29
    accro
    -0.28
     ком
    -0.28
     dying
    -0.27
    cleros
    -0.27
    POSITIVE LOGITS
     recognition
    0.88
     Recognition
    0.87
     recognizing
    0.81
     RECOGN
    0.80
     detection
    0.79
     recognize
    0.79
     riconoscimento
    0.76
    Recognition
    0.76
     Recognize
    0.76
     Recogn
    0.75
    Activations Density 0.279%

    No Known Activations