© 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. 136
    Prev
    Next
    INDEX
    Explanations

    words related to identity and familial relationships

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

    "The first," "the last," "the [adjective] of"

    np_acts-logits-general · gemini-2.0-flash

    unique roles and superlatives

    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
     betweenstory
    -0.89
     للمعارف
    -0.81
    livé
    -0.70
    vedať
    -0.64
     pelbagai
    -0.63
     BoxDecoration
    -0.62
     laterales
    -0.61
    ьаж
    -0.60
     estimés
    -0.59
    richTextPanel
    -0.58
    POSITIVE LOGITS
     only
    1.04
    only
    0.78
     recipient
    0.74
     youngest
    0.73
     sole
    0.69
     subject
    0.67
     ONLY
    0.67
     winner
    0.67
     epitome
    0.66
     oldest
    0.66
    Activations Density 0.267%

    No Known Activations