© 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. 4-GEMMASCOPE-RES-16K
    11. 230
    Prev
    Next
    INDEX
    Explanations

    references to structural concepts and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     repens
    -0.89
     Noct
    -0.84
     isoto
    -0.81
     Obf
    -0.81
     peal
    -0.78
     labial
    -0.76
     ciphertext
    -0.76
    Dispatchers
    -0.76
     anonyme
    -0.75
     veneta
    -0.75
    POSITIVE LOGITS
     structure
    2.55
     structures
    2.26
     Structure
    2.26
    structure
    2.19
    Structure
    2.07
     STRUCTURE
    2.01
     Structures
    1.95
    structures
    1.93
     STRUCTURES
    1.73
     estructura
    1.66
    Activations Density 0.100%

    No Known Activations