© 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. 938
    Prev
    Next
    INDEX
    Explanations

    words associated with themes of obligation, guilt, and consequence

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

    ending in "ant", "ent", or "ent"

    np_acts-logits-general · gemini-2.0-flash

    technical nouns and concepts

    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
    ised
    -1.05
    ed
    -1.02
    ever
    -0.91
    ities
    -0.85
    ized
    -0.82
    i
    -0.80
    e
    -0.78
    ists
    -0.76
    eyes
    -0.76
    items
    -0.74
    POSITIVE LOGITS
    ting
    0.77
    ations
    0.66
    iness
    0.63
    tttt
    0.61
    ttt
    0.61
    uous
    0.60
    ress
    0.59
    ational
    0.56
    ेड
    0.56
    ation
    0.54
    Activations Density 0.922%

    No Known Activations