© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 13-GEMMASCOPE-RES-65K
    11. 13716
    Prev
    Next
    INDEX
    Explanations

    the word "need," indicating a sense of requirement or necessity

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     themſelves
    -1.13
    ViewFeatures
    -1.12
     itſelf
    -1.00
    ſelf
    -0.99
    XtraEditors
    -0.97
     houſe
    -0.95
     himſelf
    -0.92
     ſtate
    -0.91
     Jefus
    -0.89
     ſeveral
    -0.87
    POSITIVE LOGITS
     need
    1.53
     needs
    1.33
     NEED
    1.31
    NEED
    1.30
     Need
    1.23
    need
    1.19
     needed
    1.14
    Need
    1.09
     NEEDS
    1.05
     Needs
    1.03
    Activations Density 0.050%

    No Known Activations