© 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. 6648
    Prev
    Next
    INDEX
    Explanations

    references to diversity and representation issues in film, particularly regarding race and gender

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

    criticisms and discussions of diversity and representation issues in Marvel films.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou

    references to the Marvel Cinematic Universe (MCU) and its characters, particularly in discussions about diversity and representation.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    references to the Marvel Cinematic Universe, including its films/TV titles, character and organization names, and in-universe lore terms.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    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
     Guayaquil
    -0.48
     ecuator
    -0.46
     بغداد
    -0.44
    ртка
    -0.43
     contemporáneo
    -0.42
     fotográfico
    -0.41
     historiques
    -0.39
     Lampung
    -0.39
     policial
    -0.39
     épis
    -0.38
    POSITIVE LOGITS
     Marvel
    0.92
     MCU
    0.87
    Marvel
    0.79
     Avengers
    0.78
    MCU
    0.68
    Avengers
    0.67
     Thanos
    0.66
    marvel
    0.63
     Avenger
    0.62
     marvel
    0.60
    Activations Density 0.171%

    No Known Activations