© 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. 3682
    Prev
    Next
    INDEX
    Explanations

    gerunds and present participles in the text

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

    gerund forms (words ending in "-ing") that describe actions or processes being undertaken.

    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
     quæ
    -0.73
    verifyException
    -0.71
    mobileqq
    -0.68
    Personensuche
    -0.65
     Wicidata
    -0.62
     ddelweddau
    -0.59
     مرئيه
    -0.57
    şört
    -0.57
    =$?
    -0.54
     indígen
    -0.52
    POSITIVE LOGITS
    ly
    0.63
    ting
    0.55
    g
    0.54
    GGGG
    0.49
    ding
    0.49
    gggg
    0.48
    τας
    0.46
    mi
    0.45
    οντας
    0.44
    ton
    0.43
    Activations Density 0.863%

    No Known Activations