© 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. 11988
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to excavation and lifting equipment

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

    Rope, cable, and related equipment

    np_acts-logits-general · gemini-2.0-flash

    rope and cable

    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
    chitis
    -0.67
    Legături
    -0.58
     burrows
    -0.56
     prophecies
    -0.55
     Buses
    -0.55
    phyllum
    -0.54
     otu
    -0.54
     Stamp
    -0.53
     Medley
    -0.53
    Placa
    -0.52
    POSITIVE LOGITS
     cable
    0.83
     rope
    0.80
     tension
    0.80
     wire
    0.74
     reel
    0.73
    rope
    0.70
     Rope
    0.67
    Rope
    0.66
     Cable
    0.66
     ropes
    0.66
    Activations Density 0.231%

    No Known Activations