© 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. 2-GEMMASCOPE-RES-16K
    11. 7318
    Prev
    Next
    INDEX
    Explanations

    references to the first person singular pronoun

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Theſe
    -1.43
     ―――――
    -1.24
     Beſ
    -1.23
     Anſ
    -1.18
     themſelves
    -1.11
     Monfieur
    -1.10
     ſeveral
    -1.06
     itſelf
    -1.06
     ་་
    -1.05
     ſind
    -1.01
    POSITIVE LOGITS
     I
    2.77
    I
    2.16
     i
    1.59
     O
    1.11
     J
    1.08
     A
    1.08
     M
    1.06
    Ｉ
    1.05
     я
    1.04
     F
    1.02
    Activations Density 0.408%

    No Known Activations