© 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. 2-GEMMASCOPE-RES-16K
    11. 14503
    Prev
    Next
    INDEX
    Explanations

    the quality of being thorough in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cherchés
    -0.64
     Rhi
    -0.62
    )(((
    -0.60
     Schme
    -0.58
    thie
    -0.57
     tits
    -0.57
     atheism
    -0.56
     Recipro
    -0.56
     للاسماء
    -0.55
    Converters
    -0.55
    POSITIVE LOGITS
     thoroughly
    1.08
    Gentle
    0.88
     Gentleman
    0.86
     Thorough
    0.84
     Gentle
    0.83
     thorough
    0.83
     GENTLE
    0.82
    gentle
    0.81
    Gentlemen
    0.77
    oughly
    0.76
    Activations Density 0.099%

    No Known Activations