© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 2127
    Prev
    Next
    INDEX
    Explanations

    references to notable individuals, particularly those with titles such as "Sir."

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

    starting with "Sir", "Cir", or "Mir"

    np_acts-logits-general · gemini-2.0-flash

    Sir + names, Cir + rious

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ItemBackground
    -0.88
    enance
    -0.71
    paksa
    -0.70
    kamen
    -0.70
     esternos
    -0.70
     Mako
    -0.69
    комму
    -0.68
    amation
    -0.67
     Beal
    -0.66
    ogeneity
    -0.66
    POSITIVE LOGITS
    ir
    0.87
     CIR
    0.87
    Cir
    0.84
     Kir
    0.83
     Sira
    0.83
    hir
    0.82
     KIR
    0.81
     SIR
    0.80
    Kir
    0.79
    IR
    0.79
    Activations Density 0.258%

    No Known Activations