© 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. 23-GEMMASCOPE-RES-16K
    11. 5131
    Prev
    Next
    INDEX
    Explanations

    calls to action or messages encouraging participation and awareness

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

    language describing organized, collective efforts or campaigns pursuing a specific goal, often framed with purpose clauses (e.g., “to” do something).

    oai_token-act-pair · gpt-5Triggered by @liuliujiujiu05
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     تانيه
    -0.68
     Rigby
    -0.57
    abancı
    -0.56
    ugno
    -0.54
    anskje
    -0.53
    ècie
    -0.51
     redenen
    -0.51
    ocuk
    -0.51
    ogna
    -0.51
    äler
    -0.51
    POSITIVE LOGITS
     encourage
    0.75
     ensure
    0.74
     promote
    0.71
     reunite
    0.69
     bring
    0.64
     improve
    0.64
     protect
    0.62
     increase
    0.62
     educate
    0.60
     restore
    0.60
    Activations Density 0.350%

    No Known Activations