© 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. 2320
    Prev
    Next
    INDEX
    Explanations

    names, specifically surnames and associated patterns within a context

    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
    onAttach
    -0.60
    canestro
    -0.56
    λία
    -0.55
    řel
    -0.54
     Wallflower
    -0.54
    λλά
    -0.53
    hartt
    -0.52
    blico
    -0.51
     maxi
    -0.48
    MIDDLEWARE
    -0.48
    POSITIVE LOGITS
    RegressionTest
    0.61
     pouvoit
    0.59
     numérique
    0.58
    لينكات
    0.58
    Personensuche
    0.57
     étend
    0.57
     magique
    0.57
     perpétu
    0.55
     accél
    0.55
     témo
    0.55
    Activations Density 1.238%

    No Known Activations