© 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. 4-GEMMASCOPE-RES-16K
    11. 10737
    Prev
    Next
    INDEX
    Explanations

    references to programming concepts and terms related to software assembly

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ModelExpression
    -0.64
     unknownFields
    -0.55
    página
    -0.53
    XmlAccessorType
    -0.52
    sizeCache
    -0.52
    stays
    -0.47
    oredCriteria
    -0.47
    Microkernel
    -0.46
    dataclass
    -0.46
     menerima
    -0.45
    POSITIVE LOGITS
    存于互联网档案馆
    0.68
    paksa
    0.66
    IGraphics
    0.65
     whereof
    0.64
     AssemblyCulture
    0.64
     NSCoder
    0.62
    FlatList
    0.62
     Markers
    0.61
     Riti
    0.61
    ocratic
    0.61
    Activations Density 1.476%

    No Known Activations