© 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. 14553
    Prev
    Next
    INDEX
    Explanations

    terms that indicate differences or variations in context

    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
     informée
    -0.57
     otomatig
    -0.56
     оригіналу
    -0.53
    र्फ
    -0.52
     Signalez
    -0.52
    FontOfSize
    -0.52
    ariest
    -0.51
    Smaller
    -0.49
     métro
    -0.49
    SequentialGroup
    -0.49
    POSITIVE LOGITS
     greatly
    2.18
     significantly
    2.03
     considerably
    2.02
     substantially
    1.91
     markedly
    1.74
     drastically
    1.73
     tremendously
    1.72
     heavily
    1.71
     dramatically
    1.70
     enormously
    1.67
    Activations Density 0.910%

    No Known Activations