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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 12863
    Prev
    Next
    INDEX
    Explanations

    expressions of emotions, inquiries about well-being, and discussions relating to support or understanding

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

    Adverbs that soften a statement

    np_acts-logits-general · gemini-2.0-flash

    just, simply, still, yet, only

    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
    脚注の使い方
    -0.78
    ьаж
    -0.74
    setVerticalGroup
    -0.72
    -------------</
    -0.71
     ultimately
    -0.70
     ciertamente
    -0.69
    Tazama
    -0.69
     nécessairement
    -0.68
     lenker
    -0.68
    certainly
    -0.67
    POSITIVE LOGITS
    ských
    0.49
     few
    0.49
    dasarkan
    0.49
     Schuster
    0.48
    ského
    0.48
     wenige
    0.45
     majority
    0.44
     منها
    0.44
    lyk
    0.43
    として
    0.43
    Activations Density 0.192%

    No Known Activations