© 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. 4547
    Prev
    Next
    INDEX
    Explanations

    instances of the word "best" and its variations, indicating a focus on quality or superiority

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

    Following "Best" or "best"

    np_acts-logits-general · gemini-2.0-flash

    best followed by superlatives

    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
    er
    -0.76
    an
    -0.70
    a
    -0.62
    io
    -0.60
    q
    -0.59
    k
    -0.59
    o
    -0.59
    r
    -0.56
    h
    -0.56
    ER
    -0.56
    POSITIVE LOGITS
     healthiest
    1.04
     lightest
    1.00
     darkest
    0.99
     possible
    0.99
    ariest
    0.98
     happiest
    0.97
     beſt
    0.97
    BEST
    0.95
     safest
    0.95
    possible
    0.95
    Activations Density 0.127%

    No Known Activations