© 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. 14645
    Prev
    Next
    INDEX
    Explanations

    references to notable individuals and concepts in literature and social commentary

    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
     purpoſe
    -0.91
     للاسماء
    -0.83
    Personendaten
    -0.82
    Brainz
    -0.73
     myſelf
    -0.72
     pleaſure
    -0.71
     theſe
    -0.70
     незавершена
    -0.70
    afficheront
    -0.69
     houſe
    -0.68
    POSITIVE LOGITS
     versus
    0.86
     vs
    0.84
     revisited
    0.79
     without
    0.77
     in
    0.75
    vs
    0.71
     beyond
    0.71
     at
    0.70
     meets
    0.65
     глазами
    0.65
    Activations Density 0.258%

    No Known Activations