Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 13964
    Prev
    Next
    INDEX
    Explanations

    references to soil-related components and their roles in environmental studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    twimg
    -0.71
    ClientSize
    -0.68
     conto
    -0.67
    𝒞
    -0.67
     centi
    -0.66
     centimeter
    -0.66
    Christian
    -0.65
    Conrad
    -0.63
     Christian
    -0.63
    Christopher
    -0.63
    POSITIVE LOGITS
    出版年
    0.47
    ItemLayout
    0.47
    illermo
    0.45
    abstractmethod
    0.43
     HasFactory
    0.42
    AfterViewInit
    0.40
     randonnée
    0.39
     financières
    0.39
     sagesse
    0.39
    otho
    0.39
    Activations Density 0.829%

    No Known Activations