© 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. 15301
    Prev
    Next
    INDEX
    Explanations

    technical terms and numerical data related to models and methods in scientific or mathematical contexts

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

    Mathematical or code-related expressions

    np_acts-logits-general · gemini-2.0-flash

    kidneys, reno, investigation

    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
    ToListAsync
    -0.92
     صوتيه
    -0.90
     ་་
    -0.87
    AllAfrica
    -0.84
    spesies
    -0.83
     Akismet
    -0.83
     ―――――
    -0.83
    InputBorder
    -0.82
     EnglishChoose
    -0.82
     erſten
    -0.82
    POSITIVE LOGITS
      
    0.58
       
    0.51
    …
    0.51
    lapsingToolbar
    0.50
    buttonBar
    0.49
    .
    0.49
    –
    0.48
     kohdetta
    0.47
    бурга
    0.45
    ↵↵
    0.44
    Activations Density 5.210%

    No Known Activations