© 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. 0-GEMMASCOPE-RES-16K
    11. 587
    Prev
    Next
    INDEX
    Explanations

    references to magic spells and their characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    HasAnnotation
    -0.59
     behö
    -0.56
    dientemente
    -0.54
     liknande
    -0.53
     رو
    -0.53
    jsii
    -0.52
     piede
    -0.52
    følgelig
    -0.52
    herin
    -0.51
    insatz
    -0.51
    POSITIVE LOGITS
     grammar
    0.71
     Grammar
    0.70
     diabetics
    0.68
     spelling
    0.68
    mappedBy
    0.66
     disambiguazione
    0.64
     plasma
    0.61
     ویکی‌پدیای
    0.59
    Grammar
    0.59
    drama
    0.59
    Activations Density 0.142%

    No Known Activations