© 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. 18-GEMMASCOPE-RES-16K
    11. 243
    Prev
    Next
    INDEX
    Explanations

    comparative phrases and terms related to preferences and choices

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

    followed by "the"

    np_acts-logits-general · gemini-2.0-flash

    those (plural/feminine)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     beginnetje
    -0.72
    abetes
    -0.71
    exitRule
    -0.69
     itſelf
    -0.68
     betweenstory
    -0.68
    MigrationBuilder
    -0.66
     themſelves
    -0.64
     oprot
    -0.64
     ExecuteAsync
    -0.63
     Monfieur
    -0.63
    POSITIVE LOGITS
     those
    1.29
     aquellos
    1.11
    those
    1.09
     aquellas
    1.04
    Those
    1.01
     Those
    1.00
     aqueles
    0.99
    那些
    0.89
     những
    0.89
     aquella
    0.84
    Activations Density 1.062%

    No Known Activations