© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 34-GEMMASCOPE-RES-16K
    11. 2411
    Prev
    Next
    INDEX
    Explanations

    mentions of diversity and representation issues within the Marvel Cinematic Universe

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/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.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     بغداد
    -0.52
    TAWA
    -0.49
    ртка
    -0.47
     saveiro
    -0.47
     Bagdad
    -0.46
     Baghdad
    -0.44
    شهر
    -0.44
    tanleria
    -0.44
    gebob
    -0.42
    PMT
    -0.42
    POSITIVE LOGITS
     Marvel
    0.97
     Avengers
    0.90
    Marvel
    0.86
     MCU
    0.85
    Avengers
    0.80
     Thanos
    0.75
     Avenger
    0.72
     avengers
    0.71
    marvel
    0.68
     marvel
    0.67
    Activations Density 0.195%

    No Known Activations