© 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. 19-GEMMASCOPE-RES-16K
    11. 15558
    Prev
    Next
    INDEX
    Explanations

    references to the initiation or beginnings of events or concepts

    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
    ngOnDestroy
    -0.53
     ListTile
    -0.49
    ItemLayout
    -0.48
    βε
    -0.47
    prepareStatement
    -0.47
    ptonshire
    -0.46
     prochains
    -0.46
    zzleHttp
    -0.45
     &___
    -0.45
    enterian
    -0.45
    POSITIVE LOGITS
     started
    1.96
    started
    1.72
     Started
    1.72
     began
    1.62
    Started
    1.61
     STARTED
    1.58
     originated
    1.54
     begun
    1.49
     Began
    1.46
     dimulai
    1.46
    Activations Density 0.297%

    No Known Activations