© 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. 3606
    Prev
    Next
    INDEX
    Explanations

    segments of code or mathematical expressions that involve indices and their manipulations

    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
    SpringBootTest
    -0.62
     beneficial
    -0.54
    ---|---|
    -0.52
     pimiento
    -0.50
     tối
    -0.49
    hah
    -0.48
    らしい
    -0.47
    らしく
    -0.47
    benef
    -0.45
     daß
    -0.45
    POSITIVE LOGITS
    RuleContext
    0.82
     الحره
    0.80
     ddelweddau
    0.75
    ftagPool
    0.75
     الرياضيه
    0.69
    ConstraintMaker
    0.69
     CreateTagHelper
    0.65
    IntoConstraints
    0.64
    WaitGroup
    0.64
     noqa
    0.64
    Activations Density 0.270%

    No Known Activations