© 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. 11552
    Prev
    Next
    INDEX
    Explanations

    the presence of the word "be" and variations of the word "else."

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

    Conditional "be", "else", or "had"

    np_acts-logits-general · gemini-2.0-flash

    be it / else if

    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
     Houſe
    -1.01
     itſelf
    -0.98
     Anſ
    -0.97
     myſelf
    -0.96
    ſelf
    -0.93
    ſelves
    -0.88
     Efq
    -0.87
     שוליים
    -0.86
     Reſ
    -0.86
     photolibrary
    -0.86
    POSITIVE LOGITS
     they
    1.41
     you
    1.35
     we
    1.17
     it
    1.17
     he
    1.13
     there
    1.01
     she
    0.83
     if
    0.78
    they
    0.75
     они
    0.72
    Activations Density 0.163%

    No Known Activations