© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 14193
    Prev
    Next
    INDEX
    Explanations

    metadata and structural elements within documents

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

    Email header fields (Subject, Date, Location)

    np_acts-logits-general · gemini-2.0-flash

    metadata keys: subject, date, location

    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
    <eos>
    -0.64
     meant
    -0.48
     and
    -0.44
     at
    -0.42
     more
    -0.41
    bringt
    -0.40
    mik
    -0.38
     safety
    -0.38
     `
    -0.38
     Mik
    -0.37
    POSITIVE LOGITS
    principalColumn
    1.17
     سكانية
    1.15
    Datuak
    1.14
     مشين
    1.10
     дописавши
    1.00
    tagext
    0.99
    IsContent
    0.98
     Wicidata
    0.95
    WebVitals
    0.95
    RenderAtEndOf
    0.94
    Activations Density 0.284%

    No Known Activations