© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 12978
    Prev
    Next
    INDEX
    Explanations

    terms related to participant conditions and study methodology in clinical research

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     try
    -0.52
    hidden
    -0.48
     hidden
    -0.47
     uiteindelijk
    -0.46
    try
    -0.44
     Try
    -0.42
    Hidden
    -0.41
     пыта
    -0.40
     försö
    -0.40
     veckor
    -0.40
    POSITIVE LOGITS
     snippetHide
    0.81
     AssemblyCompany
    0.80
    ViewFeatures
    0.79
    GIVEREF
    0.78
    BeginContext
    0.78
    ...");
    0.78
    ")));
    0.76
    ()]
    0.75
    )");
    0.74
     deemed
    0.73
    Activations Density 0.496%

    No Known Activations