© 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. 16-GEMMASCOPE-RES-16K
    11. 13425
    Prev
    Next
    INDEX
    Explanations

    phrases that discuss the concept of "way" in relation to actions or experiences

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

    Follows "the way" or similar phrases

    np_acts-logits-general · gemini-2.0-flash

    the way it is

    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
     noires
    -0.52
    UnsafeEnabled
    -0.46
     habido
    -0.46
     geblieben
    -0.46
     évit
    -0.45
    hafen
    -0.45
     maggiori
    -0.45
     voici
    -0.45
    multirow
    -0.45
     vote
    -0.45
    POSITIVE LOGITS
    Geplaatst
    0.72
     manner
    0.69
     worded
    0.62
     initComponents
    0.61
    manner
    0.60
    RegressionTest
    0.58
     autorytatywna
    0.56
    richTextPanel
    0.56
    Executives
    0.55
    figer
    0.55
    Activations Density 0.318%

    No Known Activations