© 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. 14600
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and decimal points

    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
    ]")]
    -1.12
    parsedMessage
    -1.02
    elemField
    -1.00
     defaultstate
    -0.97
    GEBURTSDATUM
    -0.95
    yntaxException
    -0.95
     חיצוניים
    -0.94
    SharedCtor
    -0.94
    WithIOException
    -0.94
     kasarigan
    -0.93
    POSITIVE LOGITS
    com
    0.71
     com
    0.69
    py
    0.68
    net
    0.68
    org
    0.68
    gov
    0.63
    io
    0.58
    edu
    0.56
    ru
    0.55
    js
    0.54
    Activations Density 0.355%

    No Known Activations