© 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. 7917
    Prev
    Next
    INDEX
    Explanations

    content that lacks significant activity or engagement metrics

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

    Text between paired symbols/punctuation

    np_acts-logits-general · gemini-2.0-flash

    web links and URLs

    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
    hasMoreElements
    -0.67
    Климат
    -0.65
     సౌకర్య
    -0.62
    Ссылки
    -0.60
    ✭✭
    -0.60
    Stayed
    -0.57
     Italijani
    -0.57
    ABUL
    -0.56
    Abitanti
    -0.56
    Tracce
    -0.56
    POSITIVE LOGITS
     «
    0.73
     ↑
    0.73
    tagHelperRunner
    0.71
     https
    0.71
     http
    0.68
     
    0.56
    IUrlHelper
    0.56
    ]<<"
    0.55
     "
    0.54
     ‘‘
    0.54
    Activations Density 0.053%

    No Known Activations