© 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. 18-GEMMASCOPE-RES-16K
    11. 2863
    Prev
    Next
    INDEX
    Explanations

    verbs indicating future actions or events

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

    Following "will," "team," or "strongest"

    np_acts-logits-general · gemini-2.0-flash

    expressing expectation or anticipation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     تضيفلها
    -0.74
    fjspx
    -0.64
     irgendwann
    -0.61
     picioare
    -0.60
     cesse
    -0.59
     Eventually
    -0.58
    Epilogue
    -0.58
    Eventually
    -0.58
    تقاوى
    -0.58
     Gradually
    -0.57
    POSITIVE LOGITS
    Expect
    0.90
     expecting
    0.86
     Expect
    0.86
    expect
    0.82
     expect
    0.80
     expected
    0.79
     expects
    0.72
     EXPECT
    0.71
     expectation
    0.69
     hoping
    0.68
    Activations Density 0.156%

    No Known Activations