© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 1319
    Prev
    Next
    INDEX
    Explanations

    technical terms related to astronomical measurement and observations

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

    references to telescopes and observational equipment in a scientific context

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

    telescope, Russia, Waste, FLAG, Clermont

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    发表于
    -0.67
    MemoryWarning
    -0.66
    AnchorTagHelper
    -0.63
    arum
    -0.59
    GEBURTS
    -0.59
    Bronnen
    -0.56
     ffilmiau
    -0.53
    تيجة
    -0.53
    expandindo
    -0.52
    তথ্যসূত্র
    -0.50
    POSITIVE LOGITS
    crats
    0.52
    хьтан
    0.51
     Prose
    0.49
     Deception
    0.49
     tendons
    0.49
    aways
    0.48
     Jockey
    0.47
     Irishman
    0.46
     encomp
    0.44
     المعرف
    0.44
    Activations Density 0.183%

    No Known Activations