© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 13090
    Prev
    Next
    INDEX
    Explanations

    elements and attributes related to data structure definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Numerade
    -0.62
    IVEREF
    -0.61
     Italijani
    -0.60
    PreferredItem
    -0.59
    헌
    -0.55
     skup
    -0.52
    jsxFileName
    -0.51
    けている
    -0.48
    енча
    -0.47
     Italijanski
    -0.47
    POSITIVE LOGITS
    complexContent
    0.78
     JAXB
    0.72
     RoutedEventArgs
    0.68
     JAXBElement
    0.67
    XmlType
    0.64
     }{@
    0.64
     minOccurs
    0.63
    .")]
    0.60
    UIFont
    0.59
    expects
    0.59
    Activations Density 0.004%

    No Known Activations