© 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. 12553
    Prev
    Next
    INDEX
    Explanations

    references to processes, metrics, and evaluations related to various fields like business, technology, or science

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

    This neuron activates for nouns and terms related to time, especially periods, durations, and scheduling.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    words related to time periods and durations.

    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
    Fordítás
    -0.41
    SuppressMessage
    -0.40
    TagMode
    -0.39
    Rhestr
    -0.37
    تقاوى
    -0.36
    råd
    -0.35
    .*")]
    -0.35
    出版年
    -0.34
    apimachinery
    -0.34
    agramm
    -0.33
    POSITIVE LOGITS
    featureID
    0.63
     trajectory
    0.59
     regime
    0.58
     pattern
    0.57
     structure
    0.57
     corpus
    0.57
     modality
    0.56
    structure
    0.54
     format
    0.54
     posture
    0.54
    Activations Density 1.768%

    No Known Activations