© 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. 17-GEMMASCOPE-RES-16K
    11. 8622
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate continuity or persistence over time

    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
    RegressionTest
    -0.56
    Finally
    -0.55
    Espèce
    -0.55
     pinulongan
    -0.50
     Finally
    -0.50
    findpost
    -0.49
     Finalmente
    -0.46
    finally
    -0.46
    tagHelperRunner
    -0.43
     eventualmente
    -0.43
    POSITIVE LOGITS
     inception
    1.21
     beginning
    1.03
    beginning
    0.92
     earliest
    0.92
     BEGINNING
    0.85
     Beginning
    0.84
     outset
    0.83
     início
    0.81
     beginnings
    0.80
     start
    0.80
    Activations Density 0.196%

    No Known Activations