© 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. 16-GEMMASCOPE-RES-65K
    11. 31693
    Prev
    Next
    INDEX
    Explanations

    phrases or references to concepts, objects, or entities presented in a general or abstract manner

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    things do or are

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     myſelf
    -1.03
     pleaſure
    -1.02
    ChildScrollView
    -0.96
     themſelves
    -0.94
     uſe
    -0.93
     juſt
    -0.92
     ſur
    -0.91
     ―――――
    -0.91
     ſmall
    -0.91
     ſtate
    -0.91
    POSITIVE LOGITS
     things
    1.45
    Things
    1.38
     Things
    1.35
     THINGS
    1.30
     Thing
    1.23
     thing
    1.21
    things
    1.20
     THING
    1.12
    Thing
    1.10
    THINGS
    0.98
    Activations Density 0.025%

    No Known Activations