© 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. 22-GEMMASCOPE-RES-16K
    11. 11442
    Prev
    Next
    INDEX
    Explanations

    references to location-specific nouns and their associated articles

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

    Article in Spanish, French, or Italian

    np_acts-logits-general · gemini-2.0-flash

    Los / les / negli / anciens + noun

    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
     Majefty
    -0.93
     fubject
    -0.93
     caufe
    -0.93
     purpoſe
    -0.92
     poffible
    -0.92
     itſelf
    -0.91
     reaſon
    -0.88
     ftate
    -0.88
     occafion
    -0.88
     ſtate
    -0.87
    POSITIVE LOGITS
     efforts
    0.46
     inputs
    0.42
     bonitos
    0.42
     bons
    0.39
     insights
    0.38
     possibles
    0.37
     seus
    0.37
    ושים
    0.36
    кет
    0.35
    ctivos
    0.35
    Activations Density 0.028%

    No Known Activations