© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 12334
    Prev
    Next
    INDEX
    Explanations

    instances of notable achievements and positions held by individuals

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

    Preceding past-tense verbs

    np_acts-logits-general · gemini-2.0-flash

    past tense followed by an action

    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
     gotten
    -0.69
    ônicos
    -0.68
     neighborhoods
    -0.66
    IntoConstraints
    -0.66
     behaviors
    -0.66
     behavioral
    -0.66
    ômico
    -0.65
     prioritize
    -0.65
     NSCoder
    -0.64
     lenker
    -0.64
    POSITIVE LOGITS
    horabuena
    0.68
     ably
    0.63
     ((!
    0.59
     läßt
    0.59
     daß
    0.59
     muß
    0.58
     mußten
    0.58
     désolés
    0.57
     kindly
    0.56
     skall
    0.55
    Activations Density 0.384%

    No Known Activations