Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 16067
    Prev
    Next
    INDEX
    Explanations

    references to female-led superhero films and their representation in media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     noci
    -0.45
     organis
    -0.43
    Uploaded
    -0.42
    rians
    -0.42
     Leaderboard
    -0.41
    ariato
    -0.40
     acute
    -0.40
     organisiert
    -0.40
    loyed
    -0.39
     self
    -0.39
    POSITIVE LOGITS
     sequels
    1.19
     sequel
    1.03
    franchise
    0.96
     franchise
    0.94
    expandindo
    0.90
     prequel
    0.86
     rumours
    0.85
    mybatisplus
    0.85
     reboot
    0.85
     franchises
    0.83
    Activations Density 0.285%

    No Known Activations