© 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. 14-GEMMASCOPE-RES-16K
    11. 13801
    Prev
    Next
    INDEX
    Explanations

    prepositions and conjunctions in various languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     themſelves
    -1.18
     itſelf
    -1.12
     Majefty
    -1.09
     himſelf
    -1.04
     iſt
    -1.00
     myſelf
    -1.00
     ་་
    -0.99
     ſche
    -0.97
     poffible
    -0.94
     becauſe
    -0.94
    POSITIVE LOGITS
    ]='\
    0.88
     za
    0.75
     за
    0.74
    日在
    0.74
     na
    0.70
     на
    0.69
     N
    0.68
     у
    0.67
     к
    0.67
     عن
    0.67
    Activations Density 0.020%

    No Known Activations