© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 10654
    Prev
    Next
    INDEX
    Explanations

    phrases indicating complexity or complications in a narrative or argument

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

    periods that end sentences or major structural breaks in text.

    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
     ayrıca
    -0.71
     inoltre
    -0.70
     additionally
    -0.70
     Paglinawan
    -0.68
     furthermore
    -0.67
    <?
    -0.67
     consequently
    -0.67
     також
    -0.66
    ArrowToggle
    -0.65
     также
    -0.64
    POSITIVE LOGITS
     Namely
    1.25
     namely
    1.16
     nämlich
    1.09
    namely
    0.98
     namelijk
    0.96
     nemlig
    0.93
     Firstly
    0.90
    Firstly
    0.82
     totiž
    0.82
     näm
    0.78
    Activations Density 0.668%

    No Known Activations