© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 1297
    Prev
    Next
    INDEX
    Explanations

    terms related to health and medical situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    országban
    -0.58
    nowu
    -0.57
    endphp
    -0.57
     دیکھیے
    -0.54
     hinweg
    -0.54
     mesmos
    -0.52
     nakalista
    -0.52
     kanssa
    -0.52
    ──
    -0.51
    katapos
    -0.51
    POSITIVE LOGITS
     Paglinawan
    0.74
    ﹑
    0.69
    GEBURTSDATUM
    0.67
    पया
    0.65
    ".
    
    0.62
     ComVisible
    0.62
     وتسجيلات
    0.62
    >();
    
    0.62
    」「
    0.61
    gridx
    0.61
    Activations Density 0.402%

    No Known Activations