© 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. 19-GEMMASCOPE-RES-16K
    11. 1131
    Prev
    Next
    INDEX
    Explanations

    questions and expressions of curiosity about the actions or situations described in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ConstraintMaker
    -0.87
     ivelany
    -0.82
    StoryboardSegue
    -0.80
    
    -0.73
    IntoConstraints
    -0.73
    出版年
    -0.71
    ElementException
    -0.71
    جغرافيا
    -0.71
     Roskov
    -0.70
    InvalidProtocol
    -0.68
    POSITIVE LOGITS
     interesting
    2.73
    interesting
    2.44
     Interesting
    2.25
    Interesting
    2.25
     fascinating
    2.05
     intriguing
    1.92
     interestingly
    1.91
     curious
    1.84
     interessante
    1.82
     strange
    1.82
    Activations Density 0.564%

    No Known Activations