© 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. 13091
    Prev
    Next
    INDEX
    Explanations

    references to significant events or outcomes related to elections and sports

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

    Follows prepositions or determiners

    np_acts-logits-general · gemini-2.0-flash

    outsized victory margin

    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
     HasFactory
    -0.65
    fromnode
    -0.62
     Admit
    -0.55
    dard
    -0.54
     UnityEditor
    -0.53
    jelder
    -0.51
     يتيمه
    -0.50
     Failing
    -0.49
     vivos
    -0.49
     ralenti
    -0.49
    POSITIVE LOGITS
     easily
    1.01
    easily
    0.98
     blowout
    0.94
     overwhelming
    0.93
     easy
    0.91
     landslide
    0.87
     Easily
    0.86
     dominant
    0.86
     comfortably
    0.84
     lop
    0.84
    Activations Density 0.202%

    No Known Activations