© 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. 8521
    Prev
    Next
    INDEX
    Explanations

    comparative language related to evaluation or comparison

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

    "than"

    np_acts-logits-general · gemini-2.0-flash

    comparisons with than

    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
     Jefus
    -0.78
     fhew
    -0.76
     ejus
    -0.72
     ſtate
    -0.71
     purpoſe
    -0.70
     himſelf
    -0.68
     Dolom
    -0.67
     fuch
    -0.67
    脚注の使い方
    -0.66
     ftate
    -0.66
    POSITIVE LOGITS
     THAN
    1.20
     Than
    1.09
     the
    1.02
     than
    0.95
    Than
    0.90
    THAN
    0.90
    OrEqualTo
    0.87
     what
    0.85
     ніж
    0.81
    )}_{
    0.80
    Activations Density 0.128%

    No Known Activations