© 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. 12545
    Prev
    Next
    INDEX
    Explanations

    terms related to improvements and increases in medical or nutritional contexts over time

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

    mentions of improvements or changes over time, particularly in medical or nutritional contexts.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    temporal phrases describing recent progress or change over time.

    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
     تضيفلها
    -0.59
    󠁴
    -0.57
    oa̍t
    -0.48
    ACHUSET
    -0.47
    
    -0.47
    当时
    -0.44
     ligiloj
    -0.42
    当時の
    -0.42
     lenker
    -0.42
    addPreferredGap
    -0.41
    POSITIVE LOGITS
     recent
    2.09
     lately
    1.85
    recent
    1.76
     recently
    1.64
    Recent
    1.63
     Recent
    1.57
     recente
    1.50
     reciente
    1.46
     Lately
    1.45
     since
    1.44
    Activations Density 0.593%

    No Known Activations