© 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. 2604
    Prev
    Next
    INDEX
    Explanations

    topics related to artificial intelligence and autonomous systems

    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
     torches
    -0.51
    ViewFeatures
    -0.49
    ClassNotFound
    -0.46
    Forum
    -0.45
    Cross
    -0.44
     Spree
    -0.43
     resolu
    -0.43
     Thule
    -0.43
    olar
    -0.43
     newOwner
    -0.42
    POSITIVE LOGITS
     automated
    1.53
     Automated
    1.36
    automated
    1.33
     automate
    1.33
    Automated
    1.33
     automation
    1.25
     automating
    1.25
     automati
    1.24
     automatic
    1.22
     automat
    1.15
    Activations Density 0.374%

    No Known Activations