© 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. 10-GEMMASCOPE-RES-16K
    11. 8816
    Prev
    Next
    INDEX
    Explanations

    phrases that highlight the advantages and disadvantages of various technologies or methods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/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.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    expandindo
    -0.79
     esternos
    -0.75
    AndEndTag
    -0.74
     estekak
    -0.72
     ostavi
    -0.68
     JAXBElement
    -0.66
     IBOutlet
    -0.65
     nakalista
    -0.65
    jspb
    -0.64
     >=",
    -0.62
    POSITIVE LOGITS
     benefits
    1.44
     advantages
    1.41
     Benefits
    1.31
     BENEFITS
    1.27
    Benefits
    1.26
     benefit
    1.23
     Advantages
    1.22
    Advantages
    1.16
    benefits
    1.16
    BENEFITS
    1.14
    Activations Density 0.275%

    No Known Activations