© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 12587
    Prev
    Next
    INDEX
    Explanations

    references to application materials and requirements for fellowships or grant proposals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Meksiku
    -0.57
    imanapun
    -0.57
     disfrut
    -0.55
    regler
    -0.54
    /*
    -0.53
     pamię
    -0.53
     ricordare
    -0.53
     fréquent
    -0.53
     veroor
    -0.52
     remembering
    -0.52
    POSITIVE LOGITS
     demonstrated
    0.71
     demonstrate
    0.70
     proven
    0.68
     demonstrating
    0.68
     assurances
    0.67
     promises
    0.67
     promised
    0.65
     prove
    0.65
     demonstra
    0.65
     assurance
    0.65
    Activations Density 0.346%

    No Known Activations