© 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. 2-GEMMASCOPE-RES-16K
    11. 6512
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "magic"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cister
    -0.72
    Personensuche
    -0.70
     ewes
    -0.69
     Ibsen
    -0.69
     ostavi
    -0.68
    osoba
    -0.67
     Giud
    -0.67
     ControllerBase
    -0.67
     AssemblyTitle
    -0.66
     useAppContext
    -0.65
    POSITIVE LOGITS
     magic
    3.75
     Magic
    3.45
    Magic
    3.36
    magic
    3.35
     MAGIC
    3.00
    MAGIC
    2.71
     magical
    2.55
     magia
    2.45
     magique
    2.34
    magical
    2.30
    Activations Density 0.038%

    No Known Activations