© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 14289
    Prev
    Next
    INDEX
    Explanations

    references to factual information or evidence in a legal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    jenih
    -0.55
     rius
    -0.52
    seguida
    -0.52
     khu
    -0.52
    bootstrapcdn
    -0.51
     понрави
    -0.51
     Âu
    -0.51
    registered
    -0.50
    DotNetBar
    -0.49
    好好的
    -0.49
    POSITIVE LOGITS
    !("
    0.88
     facts
    0.87
     '-
    0.82
    ('-
    0.81
     "-
    0.81
    facts
    0.73
     discipline
    0.73
    ](#
    0.72
    GEBURTSDATUM
    0.72
     steady
    0.70
    Activations Density 0.141%

    No Known Activations