© 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. 8613
    Prev
    Next
    INDEX
    Explanations

    information related to medical treatments and procedures

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

    "AUD" or "Au" (gold symbol) followed by other tokens

    np_acts-logits-general · gemini-2.0-flash

    AUD

    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
     propOrder
    -0.71
     Trenton
    -0.63
    RenderAtEndOf
    -0.63
     Slade
    -0.60
     Trotter
    -0.59
     Simeon
    -0.56
     Winfield
    -0.56
    providedIn
    -0.55
     Roper
    -0.55
     Kiy
    -0.55
    POSITIVE LOGITS
     Au
    2.15
    Au
    1.99
    au
    1.83
     au
    1.80
     AU
    1.76
    AU
    1.73
     audit
    1.71
     AUD
    1.69
    Aud
    1.67
    AUD
    1.66
    Activations Density 0.416%

    No Known Activations