© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 19-GEMMASCOPE-RES-16K
    11. 4736
    Prev
    Next
    INDEX
    Explanations

    references to specific scientific concepts or terms, particularly in the context of mathematical and physical theories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bagus
    -0.55
     Défense
    -0.52
    poco
    -0.51
     sanguí
    -0.51
     domani
    -0.51
     bodyParser
    -0.48
     cabeça
    -0.48
     cuore
    -0.48
     tomorrow
    -0.47
     backless
    -0.47
    POSITIVE LOGITS
     AssemblyCulture
    0.97
     total
    0.78
    SharedDtor
    0.75
     relation
    0.73
     EconPapers
    0.70
     presence
    0.70
    oa̍t
    0.67
     present
    0.66
    InitVars
    0.65
     corresponding
    0.63
    Activations Density 1.685%

    No Known Activations