© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 9325
    Prev
    Next
    INDEX
    Explanations

    references to sources and citations in text

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

    "source" or "sources"

    np_acts-logits-general · gemini-2.0-flash

    the word source

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ArgumentParser
    -0.78
    WriteBarrier
    -0.69
    complexContent
    -0.66
    AsUp
    -0.66
     الرياضيه
    -0.64
    TypedDataSet
    -0.63
     tartalomajánló
    -0.60
    EndProject
    -0.59
    Демографія
    -0.58
    delwed
    -0.58
    POSITIVE LOGITS
     source
    4.37
    source
    3.83
     Source
    3.71
    Source
    3.48
     sources
    3.46
     SOURCE
    3.20
     Sources
    2.98
    sources
    2.83
    ource
    2.82
    SOURCE
    2.80
    Activations Density 0.423%

    No Known Activations