© 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. 55
    Prev
    Next
    INDEX
    Explanations

    references to online communities and culture, particularly related to 4chan and internet memes

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

    Internet culture references and meme terminology (4chan, Anonymous, trolls, lolcats, Rule 34, etc.).

    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
     récord
    -0.36
    SharedCtor
    -0.36
    とっても
    -0.35
    Chicago
    -0.35
     sagesse
    -0.35
    Liebe
    -0.34
     (!)
    -0.34
    resiasi
    -0.34
     cartão
    -0.34
    siasi
    -0.34
    POSITIVE LOGITS
     faggot
    0.65
     kek
    0.64
     nigger
    0.62
    fag
    0.61
     cuck
    0.60
     memes
    0.59
    inb
    0.58
     meme
    0.57
     retard
    0.56
    ViewInit
    0.56
    Activations Density 0.202%

    No Known Activations