© 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. 15920
    Prev
    Next
    INDEX
    Explanations

    coding-related terms and phrases

    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
     estadía
    -1.02
    ônicos
    -1.02
    ônico
    -0.99
     afuera
    -0.89
     confiable
    -0.88
    êmica
    -0.86
     computadora
    -0.84
    ônica
    -0.80
    êmios
    -0.80
     Administrativna
    -0.80
    POSITIVE LOGITS
     fichero
    0.65
    fich
    0.64
     costes
    0.62
     coger
    0.58
    Fiche
    0.56
    ITV
    0.55
     posteriori
    0.55
     £
    0.54
     acabó
    0.54
     ITV
    0.53
    Activations Density 0.032%

    No Known Activations