© 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. 20-GEMMASCOPE-RES-16K
    11. 264
    Prev
    Next
    INDEX
    Explanations

    transitional words and phrases that indicate a continuation or addition of information

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

    Adverbial discourse markers

    np_acts-logits-general · gemini-2.0-flash

    further, also, importantly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    principalColumn
    -0.69
    NUMX
    -0.66
     sumpay
    -0.65
     linkovi
    -0.62
    complexContent
    -0.62
    InjectAttribute
    -0.61
    WebElementEntity
    -0.61
     otomatig
    -0.61
     SafeMath
    -0.61
     محفوظة
    -0.60
    POSITIVE LOGITS
     importantly
    0.96
     conversely
    0.62
     estimés
    0.61
    tably
    0.60
     Importantly
    0.60
     Conversely
    0.59
    ingly
    0.58
    Conversely
    0.55
    ificantly
    0.55
    ly
    0.55
    Activations Density 0.399%

    No Known Activations