© 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. 1-GEMMASCOPE-RES-16K
    11. 7756
    Prev
    Next
    INDEX
    Explanations

    specific components and identifiers related to software projects, especially in Maven configurations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    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
    -0.66
     stringBuilder
    -0.65
     Ott
    -0.54
     لديك
    -0.52
    HomeAsUp
    -0.52
     Indian
    -0.52
     memory
    -0.52
    \{\\
    -0.51
     extranjera
    -0.51
     Ind
    -0.51
    POSITIVE LOGITS
     Delegate
    0.76
    Delegate
    0.70
     delegate
    0.69
    NameInMap
    0.69
    Portail
    0.68
    modelBuilder
    0.66
     beneficiary
    0.64
    ObjectContext
    0.64
    artifactId
    0.63
    webElementGuid
    0.63
    Activations Density 2.379%

    No Known Activations