© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 9008
    Prev
    Next
    INDEX
    Explanations

    components and features of furniture or appliances

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

    Things that can be adjusted, folded, or retracted

    np_acts-logits-general · gemini-2.0-flash

    fold, retract, detach, adjustable

    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
    ContentAsync
    -0.80
     ویکی‌پدی
    -0.62
     Plaster
    -0.59
     gmina
    -0.57
    contentLoaded
    -0.57
    rinfo
    -0.55
     gevol
    -0.55
     calcetines
    -0.53
     doméstico
    -0.53
    Processed
    -0.53
    POSITIVE LOGITS
     adjustable
    0.92
     removable
    0.88
     detachable
    0.85
     easily
    0.83
     retractable
    0.78
     foldable
    0.78
     collapsible
    0.76
    Adjustable
    0.73
     fold
    0.71
     swivel
    0.70
    Activations Density 0.293%

    No Known Activations