© 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. 21-GEMMASCOPE-RES-16K
    11. 9311
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically names and titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Monfieur
    -1.10
     Theſe
    -0.85
     Jefus
    -0.79
     Verſ
    -0.77
     itſelf
    -0.76
     ―――――
    -0.75
     Cæsar
    -0.74
     myſelf
    -0.71
     fidé
    -0.70
     Reſ
    -0.70
    POSITIVE LOGITS
    :+:
    0.56
    ранже
    0.55
     Baillargeon
    0.53
    AndEndTag
    0.52
    hu
    0.51
     de
    0.50
    WithIOException
    0.48
    SharedDtor
    0.48
    égard
    0.48
    ot
    0.46
    Activations Density 0.218%

    No Known Activations