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. 20-GEMMASCOPE-RES-16K
    6. 10993
    Prev
    Next
    INDEX
    Explanations

    chemical compounds and their synthesis processes

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

    Compounds and chemical substituents

    np_acts-logits-general · gemini-2.0-flash

    chemical compound substituents

    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
     kasarigan
    -0.87
    TypedDataSet
    -0.79
    PreferredItem
    -0.64
    StructEnd
    -0.62
     Teig
    -0.62
     Roskov
    -0.60
     propOrder
    -0.59
    getMenuInflater
    -0.59
    vie
    -0.57
     ddelweddau
    -0.57
    POSITIVE LOGITS
     methyl
    0.46
    busch
    0.45
     textStatus
    0.44
    ceto
    0.44
    érature
    0.43
     фе
    0.43
    erequisites
    0.43
    kull
    0.43
     camiseta
    0.43
     Nachfolger
    0.42
    Activations Density 0.434%

    No Known Activations