© 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. 12501
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to foundations and organizational structures

    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
     ạ
    -0.77
    uyasha
    -0.75
     Bengals
    -0.75
     pliers
    -0.75
    luigi
    -0.73
     Neale
    -0.73
     Virol
    -0.72
     végétale
    -0.70
     Hick
    -0.70
     écl
    -0.70
    POSITIVE LOGITS
     Foundation
    1.50
     foundation
    1.49
     foundations
    1.43
    Foundations
    1.41
    Foundation
    1.39
    foundation
    1.36
     FOUNDATION
    1.35
     Foundations
    1.31
     fondation
    0.93
     Fondation
    0.89
    Activations Density 0.106%

    No Known Activations