© 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. 160
    Prev
    Next
    INDEX
    Explanations

    phrases related to environmental work and community engagement

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

    studies and assessments

    np_acts-logits-general · gemini-2.0-flash

    study and assessment

    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
     Whilst
    -1.38
    Whilst
    -1.32
     whilst
    -1.13
     läßt
    -0.87
     enquiry
    -0.83
    ”!
    -0.82
     daß
    -0.81
    )!
    -0.81
     Schluß
    -0.78
     hereof
    -0.78
    POSITIVE LOGITS
     ifølge
    0.92
     
    0.87
     pihaknya
    0.83
     ``
    0.81
     Tuesday
    0.79
     Sebab
    0.79
     staffers
    0.78
     ¦
    0.78
     Thursday
    0.77
     Wednesday
    0.75
    Activations Density 0.925%

    No Known Activations