© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 7783
    Prev
    Next
    INDEX
    Explanations

    connections and references to neighboring elements or adjacency in various contexts

    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
    GEBURTSDATUM
    -0.63
    XmlAccessType
    -0.58
    Erstellt
    -0.49
    InputTagHelper
    -0.47
    ZIE
    -0.43
     ujednoznacz
    -0.41
     split
    -0.40
    BufferException
    -0.40
    <thead>
    -0.40
    Descriere
    -0.39
    POSITIVE LOGITS
     nearby
    2.87
     neighboring
    2.86
     neighbouring
    2.80
     adjacent
    2.59
     neighbor
    2.56
     neighbors
    2.55
     neighbours
    2.49
     neighbour
    2.44
    neighbor
    2.43
    nearby
    2.42
    Activations Density 0.613%

    No Known Activations