© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 1758
    Prev
    Next
    INDEX
    Explanations

    prepositions and articles in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PerformLayout
    -0.87
     photolibrary
    -0.82
    ]--;
    -0.80
     ―――――
    -0.79
    mybatisplus
    -0.76
     Lambeth
    -0.75
    dersfield
    -0.74
     imprimible
    -0.73
     '*':
    -0.72
     '/':
    -0.72
    POSITIVE LOGITS
     fee
    0.56
     Fee
    0.55
     Fees
    0.54
     On
    0.54
     om
    0.54
    道
    0.53
     fuite
    0.52
    行
    0.51
     doPost
    0.50
     FEES
    0.49
    Activations Density 0.087%

    No Known Activations