© 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. 11389
    Prev
    Next
    INDEX
    Explanations

    materials that provide cushioning and support

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

    padding, soft materials, or cushioning

    np_acts-logits-general · gemini-2.0-flash

    foam cushioning and rolling

    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
     inheritance
    -0.64
    inheritance
    -0.62
    cipa
    -0.58
     Inheritance
    -0.57
    fingerprint
    -0.56
    onActivityResult
    -0.56
     Duarte
    -0.55
    rungsseite
    -0.55
    unlocked
    -0.54
     CreateTagHelper
    -0.54
    POSITIVE LOGITS
     foam
    1.19
     padding
    1.19
     cushioning
    1.07
     cushion
    1.03
     Foam
    1.00
     cushions
    0.94
     Cushi
    0.92
    foam
    0.92
    padding
    0.92
     Padding
    0.91
    Activations Density 0.261%

    No Known Activations