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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 19-GEMMASCOPE-RES-16K
    6. 15754
    Prev
    Next
    INDEX
    Explanations

    references to data structures in programming, particularly related to programming languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    expandindo
    -0.93
     Eud
    -0.74
    oa̍t
    -0.73
    Referințe
    -0.72
     Viceroy
    -0.67
     HED
    -0.67
     OMITBAD
    -0.65
     Italijani
    -0.64
     ESD
    -0.63
     Shakspeare
    -0.62
    POSITIVE LOGITS
     struct
    0.64
    struct
    0.64
     {
    0.62
    mnop
    0.59
    ly
    0.58
     {
    
    0.57
    **/
    
    0.54
    AGEM
    0.53
    :✨
    0.53
    struktion
    0.53
    Activations Density 0.050%

    No Known Activations