© 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. 0-GEMMASCOPE-RES-16K
    11. 9048
    Prev
    Next
    INDEX
    Explanations

    references to fluctuations and variations in scientific contexts, particularly related to dynamics and genetic variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     endblock
    -0.57
     frontale
    -0.47
     await
    -0.47
     esterna
    -0.45
    rag
    -0.44
     Mancini
    -0.43
    ьера
    -0.43
    Win
    -0.42
     húmedo
    -0.42
    věr
    -0.42
    POSITIVE LOGITS
    RegistryLite
    0.88
    Portály
    0.88
     ProtoMessage
    0.86
    клопе
    0.82
     fluctuations
    0.78
     disambiguazione
    0.78
    MessageTagHelper
    0.77
    rungsseite
    0.72
     stabil
    0.71
    IsContent
    0.70
    Activations Density 2.990%

    No Known Activations