© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 13-GEMMASCOPE-RES-65K
    11. 18757
    Prev
    Next
    INDEX
    Explanations

    elements related to structured data definitions and attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    FieldBuilder
    -0.80
     NSCoder
    -0.73
    SharedDtor
    -0.71
    LookAnd
    -0.67
     nakalista
    -0.66
     ivelany
    -0.66
    存于互联网档案馆
    -0.64
    ampiyon
    -0.64
     asphalt
    -0.62
    Хьажоргаш
    -0.62
    POSITIVE LOGITS
    }{*}{
    0.45
    })));
    0.43
     исто
    0.43
    viewport
    0.42
     http
    0.42
     cadeiras
    0.42
     verwij
    0.42
     sillas
    0.41
     domínio
    0.41
    fhir
    0.41
    Activations Density 0.159%

    No Known Activations