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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 11815
    Prev
    Next
    INDEX
    Explanations

    terms related to Lua programming and its libraries

    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
     Miles
    -0.60
    Miles
    -0.59
     Toma
    -0.55
     parseFrom
    -0.51
     Hudson
    -0.50
     Spirito
    -0.46
     '\\;'
    -0.46
     Clancy
    -0.46
     bombe
    -0.45
     Vikipedi
    -0.44
    POSITIVE LOGITS
     Lua
    1.16
    Lua
    1.14
    lua
    1.08
     lua
    1.03
     Henrique
    0.62
     Honig
    0.61
    luas
    0.60
    UALA
    0.59
    èdia
    0.58
     Jamaican
    0.57
    Activations Density 0.115%

    No Known Activations