© 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. 17-GEMMASCOPE-RES-16K
    11. 4756
    Prev
    Next
    INDEX
    Explanations

    phrases and expressions that downplay the significance of a subject or situation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     only
    -0.69
    only
    -0.65
    Only
    -0.61
     بيها
    -0.56
     AAV
    -0.54
    ONLY
    -0.54
    UnusedPrivate
    -0.53
     ONLY
    -0.52
     langsung
    -0.51
    unico
    -0.50
    POSITIVE LOGITS
    Tembelea
    0.71
     صوتيه
    0.63
    SequentialGroup
    0.63
    mybatisplus
    0.61
    =")
    0.59
    دانشنامهٔ
    0.59
    uidado
    0.59
    htë
    0.57
    ArgumentParser
    0.57
     للاسماء
    0.57
    Activations Density 0.178%

    No Known Activations