© 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. 24-GEMMASCOPE-RES-16K
    11. 7637
    Prev
    Next
    INDEX
    Explanations

    phrases pertaining to incidents, particularly involving crime, violence, and their legal repercussions

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

    events or affairs

    np_acts-logits-general · gemini-2.0-flash

    incidents occurring or involving

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    calipsis
    -0.56
    eloma
    -0.55
     sẵn
    -0.52
    mtrl
    -0.52
    öglichkeiten
    -0.50
    ROG
    -0.49
    azzo
    -0.49
     existence
    -0.49
    有意
    -0.48
    gania
    -0.48
    POSITIVE LOGITS
     involving
    1.57
     occurring
    1.14
     occurred
    1.07
     waarbij
    1.03
     INVOL
    1.02
    volving
    0.97
     ocurrido
    0.89
     occured
    0.89
     melibatkan
    0.88
     happening
    0.88
    Activations Density 0.568%

    No Known Activations