© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 132
    Prev
    Next
    INDEX
    Explanations

    keywords and references related to resources in a technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    references to resources in a networking or programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    resource group

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelperRunner
    -0.66
    OGND
    -0.65
     femmin
    -0.60
    Datuak
    -0.58
     attenuation
    -0.55
    enumi
    -0.54
    ContentAsync
    -0.53
    ParallelGroup
    -0.53
     Lafayette
    -0.52
    ViewImports
    -0.51
    POSITIVE LOGITS
    IsMutable
    0.62
     RES
    0.62
    URLException
    0.60
     Resource
    0.58
     imageNamed
    0.57
    lood
    0.57
     getResource
    0.57
    verwijspagina
    0.56
    URIS
    0.56
     resource
    0.56
    Activations Density 0.028%

    No Known Activations