Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 5347
    Prev
    Next
    INDEX
    Explanations

    technical phrases and terms in mathematical contexts

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

    after the word "the" in mathematical expressions

    np_acts-logits-general · gemini-2.0-flash

    maps, sequence, process, action

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kuiten
    -0.52
     specchio
    -0.49
    ლ
    -0.47
    ุ
    -0.45
    ژه
    -0.45
    â
    -0.45
    召
    -0.44
     podr
    -0.43
     licensed
    -0.42
     romántico
    -0.42
    POSITIVE LOGITS
     disambiguazione
    0.90
    RectangleBorder
    0.80
     Chwiliwch
    0.80
    rungsseite
    0.79
    цездатний
    0.79
    出版年
    0.78
    AndEndTag
    0.78
    Jereo
    0.77
    Autoritní
    0.76
     Мексичка
    0.76
    Activations Density 1.084%

    No Known Activations