© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 6886
    Prev
    Next
    INDEX
    Explanations

    content that emphasizes quality and craftsmanship in manufacturing

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

    Quality control/assurance processes

    np_acts-logits-general · gemini-2.0-flash

    meticulously manufactured products and personnel

    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
     bezeichneter
    -0.64
     plötzlich
    -0.61
    出版年
    -0.59
     Надо
    -0.54
     <=",
    -0.54
    ISupport
    -0.54
     repente
    -0.53
     pageable
    -0.53
    Apparently
    -0.52
    enseignements
    -0.52
    POSITIVE LOGITS
     meticulously
    1.08
     carefully
    1.06
     rigorously
    1.05
     cuidadosamente
    1.01
     ensures
    0.98
     guaranteeing
    0.94
     ensuring
    0.94
     guarantee
    0.92
     Carefully
    0.91
     soigneusement
    0.90
    Activations Density 0.225%

    No Known Activations