© 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. 5-GEMMASCOPE-RES-16K
    11. 3382
    Prev
    Next
    INDEX
    Explanations

    instances of user interactions related to clicking actions in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     normes
    -0.52
    ]='\
    -0.49
     hvor
    -0.48
     teljesen
    -0.48
    ערכת
    -0.48
    EntityManager
    -0.47
    @[
    -0.47
    {{-
    -0.46
     enää
    -0.46
     meille
    -0.46
    POSITIVE LOGITS
    click
    2.03
     click
    1.96
    Click
    1.85
     clicks
    1.84
     Click
    1.80
     clicked
    1.76
     CLICK
    1.63
     clicking
    1.62
    CLICK
    1.61
    clicking
    1.58
    Activations Density 0.048%

    No Known Activations