© 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. 16-GEMMASCOPE-RES-16K
    11. 1279
    Prev
    Next
    INDEX
    Explanations

    terms related to baby products, specifically diapers and covers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Comes before or after URLs or store names

    np_acts-logits-general · gemini-2.0-flash

    commerce and sales

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/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.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PerformLayout
    -0.80
    tagHelperRunner
    -0.79
     kasarigan
    -0.77
    InjectAttribute
    -0.76
     препратки
    -0.75
     tartalomajánló
    -0.72
    Atsauces
    -0.72
    ISupport
    -0.71
     mergeFrom
    -0.66
     ddelweddau
    -0.62
    POSITIVE LOGITS
     http
    0.64
     suelen
    0.59
     www
    0.56
    http
    0.56
    还可以
    0.55
     also
    0.55
     bagus
    0.54
    おすすめです
    0.54
     usually
    0.54
     costuma
    0.53
    Activations Density 0.328%

    No Known Activations