© 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. 17-GEMMASCOPE-RES-16K
    11. 12269
    Prev
    Next
    INDEX
    Explanations

    architectural details and features related to church design

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GOTREF
    -0.66
     Gallimard
    -0.61
     Monfieur
    -0.61
     linearized
    -0.60
     beep
    -0.58
     swear
    -0.57
    évaluateur
    -0.57
    EndInit
    -0.56
     mountains
    -0.56
     stubble
    -0.56
    POSITIVE LOGITS
     decorative
    0.81
     ornate
    0.81
     decoration
    0.72
     decorate
    0.72
     decorated
    0.70
     Decorative
    0.67
     ornamental
    0.67
    decorative
    0.67
     decorating
    0.66
     decorativos
    0.65
    Activations Density 0.152%

    No Known Activations