© 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. 22-GEMMASCOPE-RES-16K
    11. 431
    Prev
    Next
    INDEX
    Explanations

    references to machine learning concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "Machine" followed by "learning"

    np_acts-logits-general · gemini-2.0-flash

    machine learning and machines

    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
    Not in Any Lists

    No Comments

    Negative Logits
    __(/*!
    -0.79
    attendre
    -0.73
    orianCalendar
    -0.66
    ButterKnife
    -0.63
     Träger
    -0.62
     Hoyt
    -0.61
    htaccess
    -0.61
     dàng
    -0.61
    hips
    -0.59
     useParams
    -0.59
    POSITIVE LOGITS
    Machines
    0.97
     machines
    0.91
     Machines
    0.83
    machines
    0.80
    gun
    0.78
     Gun
    0.77
     guns
    0.73
     Machine
    0.72
     learning
    0.72
     gun
    0.72
    Activations Density 0.084%

    No Known Activations