© 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. 6778
    Prev
    Next
    INDEX
    Explanations

    phrases indicating certainty or clarity regarding decisions and outcomes

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

    Describes something as obvious, simple, or natural

    np_acts-logits-general · gemini-2.0-flash

    easy, natural, obvious decisions

    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
    MongoClient
    -0.57
     nahilalakip
    -0.52
     мәкал
    -0.51
    MemoryWarning
    -0.49
    SourceChecksum
    -0.49
     Grind
    -0.48
    cemment
    -0.48
    setContentView
    -0.48
    HasAnnotation
    -0.47
    addCriterion
    -0.47
    POSITIVE LOGITS
     obvious
    0.80
     naturellement
    0.80
     naturally
    0.79
     naturalmente
    0.77
     logically
    0.75
     intuitively
    0.72
     évidence
    0.71
     unsur
    0.71
     effortlessly
    0.71
    ISupport
    0.71
    Activations Density 0.198%

    No Known Activations