© 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. 12743
    Prev
    Next
    INDEX
    Explanations

    complex scientific terms and concepts related to numerical methods and theoretical predictions

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

    academic text in scientific papers, particularly physics and mathematics papers with equations and technical discussions of experimental results.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    technical and scientific terminology, particularly mathematical notation and formal academic language.

    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
    Fos
    -0.49
    RTLR
    -0.48
     PPS
    -0.46
     scri
    -0.46
     psychos
    -0.44
    Clik
    -0.44
     FOS
    -0.44
     SUD
    -0.42
     Xy
    -0.42
     المعيارى
    -0.42
    POSITIVE LOGITS
     disagrees
    0.56
     predicted
    0.54
     Daß
    0.54
     agreement
    0.52
     disagreement
    0.51
     disagree
    0.51
     experimentally
    0.50
     Autoren
    0.49
     qualitatively
    0.48
     inferred
    0.46
    Activations Density 2.937%

    No Known Activations