© 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. 31-GEMMASCOPE-RES-16K
    11. 10955
    Prev
    Next
    INDEX
    Explanations

    questions and discussions related to contributions and acknowledgments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    acknowledgments and credits sections listing names and affiliations of contributors.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     undersø
    -0.50
     samostat
    -0.50
     schoenen
    -0.48
     množství
    -0.47
     kracht
    -0.47
     économies
    -0.47
     samodziel
    -0.47
     nødven
    -0.47
     liknande
    -0.47
     vhodné
    -0.46
    POSITIVE LOGITS
     Dr
    1.08
     John
    0.99
     David
    0.83
     Michael
    0.82
    Dr
    0.82
     Professor
    0.77
     Drs
    0.75
     Robert
    0.75
     Richard
    0.75
     Mr
    0.73
    Activations Density 3.963%

    No Known Activations