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. 18-GEMMASCOPE-RES-16K
    6. 10250
    Prev
    Next
    INDEX
    Explanations

    terms related to chemical synthesis and characterization of catalysts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     wrong
    -0.71
    wrong
    -0.60
     correct
    -0.56
     incorrect
    -0.53
     absch
    -0.53
     right
    -0.51
     تضيفلها
    -0.51
    correct
    -0.50
     дописавши
    -0.50
    chium
    -0.49
    POSITIVE LOGITS
     Surface
    0.72
     surface
    0.72
     SURFACE
    0.67
     Oberfläche
    0.67
    Surface
    0.66
     powierzchni
    0.62
     Wikimedijinoj
    0.61
     nano
    0.61
    üstü
    0.61
     oppervlak
    0.61
    Activations Density 0.796%

    No Known Activations