© 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-2-9B
    7. Residual Stream - 16k
    9. 27-GEMMASCOPE-RES-16K
    11. 9714
    Prev
    Next
    INDEX
    Explanations

    terms relating to user actions and capabilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kasarigan
    -0.69
    
    -0.63
    expandindo
    -0.60
    RTLR
    -0.56
    uxxxx
    -0.55
     surla
    -0.52
    SPJ
    -0.51
    GEBURTSDATUM
    -0.49
     nakalista
    -0.47
     initComponents
    -0.47
    POSITIVE LOGITS
     themselves
    0.85
     their
    0.71
    themselves
    0.63
    their
    0.57
     Their
    0.57
     ihre
    0.56
    Their
    0.56
     själva
    0.55
     ihren
    0.52
     ihr
    0.50
    Activations Density 0.609%

    No Known Activations