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

    Neuronpedia

    Jacobian LensNEW
    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. 5-GEMMASCOPE-RES-16K
    11. 5661
    Prev
    Next
    INDEX
    Explanations

    wording that expresses uncertainty or possibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pleaſure
    -0.72
     Jefus
    -0.71
     ſp
    -0.69
     poule
    -0.68
     Wyman
    -0.65
     Guayaquil
    -0.63
     Jungs
    -0.63
     Чар
    -0.62
     Cooley
    -0.62
     Crawley
    -0.61
    POSITIVE LOGITS
     perhaps
    2.05
    perhaps
    1.96
     maybe
    1.85
     Perhaps
    1.82
    maybe
    1.79
    Perhaps
    1.78
    anskje
    1.69
    Maybe
    1.66
     Maybe
    1.62
     quizás
    1.59
    Activations Density 0.061%

    No Known Activations