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. 16090
    Prev
    Next
    INDEX
    Explanations

    references to significant social events and their contexts

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

    referring to time periods

    np_acts-logits-general · gemini-2.0-flash

    specific past events

    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
     tonight
    -1.08
     tomorrow
    -1.03
    rungsseite
    -0.91
    tomorrow
    -0.89
     komende
    -0.87
    来週
    -0.87
     demain
    -0.85
    Tomorrow
    -0.83
    ientôt
    -0.79
    RenderAtEndOf
    -0.79
    POSITIVE LOGITS
     damals
    1.46
    当时的
    1.45
    當時
    1.44
    当时
    1.40
    当時は
    1.33
    那时候
    1.32
    当時
    1.22
     damaligen
    1.20
    当時の
    1.17
    那时
    1.14
    Activations Density 0.567%

    No Known Activations