© 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-2-2B
    7. Residual Stream - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 7538
    Prev
    Next
    INDEX
    Explanations

    references to heroes, particularly in the context of superhero narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     photolibrary
    -0.87
     gales
    -0.84
     bushels
    -0.82
     animé
    -0.81
    Personensuche
    -0.79
     виправивши
    -0.79
     Coyote
    -0.77
     myſelf
    -0.76
     itſelf
    -0.75
     Prehistoric
    -0.75
    POSITIVE LOGITS
     hero
    1.01
     heroes
    0.86
     Hero
    0.77
    hero
    0.73
     héroes
    0.73
     Heroes
    0.68
    remarks
    0.66
    Hero
    0.64
     Bel
    0.59
    英雄
    0.59
    Activations Density 0.086%

    No Known Activations