© 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 - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 149
    Prev
    Next
    INDEX
    Explanations

    instances of organizational structures and processes related to control and management

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

    following "to" or "could"

    np_acts-logits-general · gemini-2.0-flash

    do easily or freely

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     כדי
    -0.57
    出版年
    -0.54
     endeavouring
    -0.53
     vouloir
    -0.50
     need
    -0.50
     perdere
    -0.49
    Enllaces
    -0.48
     want
    -0.48
    need
    -0.48
     tratando
    -0.47
    POSITIVE LOGITS
     easily
    1.39
     freely
    1.19
    easily
    1.17
     Easily
    1.12
    Easily
    1.11
     comfortably
    1.06
     facilement
    1.04
     safely
    1.03
     facilmente
    0.98
     fácilmente
    0.97
    Activations Density 0.341%

    No Known Activations