© 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. 4-GEMMASCOPE-RES-16K
    11. 11458
    Prev
    Next
    INDEX
    Explanations

    negative contractions, particularly "doesn't."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    toBe
    -0.71
     varit
    -0.61
     wären
    -0.60
     թվական
    -0.58
    wares
    -0.57
    aternary
    -0.56
    اعد
    -0.55
     seront
    -0.54
    ریح
    -0.53
     sebelumnya
    -0.53
    POSITIVE LOGITS
     do
    0.92
     DO
    0.91
    httphttps
    0.88
     does
    0.86
     Does
    0.85
     DOES
    0.84
    DOES
    0.82
    does
    0.81
     didst
    0.80
    ും
    0.77
    Activations Density 0.239%

    No Known Activations