© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 3073
    Prev
    Next
    INDEX
    Explanations

    references to methods and techniques used in scientific research, particularly statistical analyses and experimental procedures

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    scientific methodology descriptions, particularly when referring to techniques, methods, instruments, or materials used in research.

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

    descriptions of methodologies and techniques used in scientific procedures.

    oai_token-act-pair · claude-4-5-haiku
    Triggered 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
    Negative Logits
    tvguidetime
    -0.54
    erçe
    -0.49
     EconPapers
    -0.47
    windowFixed
    -0.47
    ViewInit
    -0.46
     utafitiHapana
    -0.45
     kaarangay
    -0.45
    ThemeOverlay
    -0.45
    FunctionFlags
    -0.44
    出版年
    -0.44
    POSITIVE LOGITS
     used
    3.05
     Used
    2.48
    Used
    2.48
    used
    2.47
     digunakan
    2.19
     USED
    2.19
     usado
    2.05
     utilisé
    2.05
     utilizado
    1.96
     utilized
    1.95
    Activations Density 1.979%

    No Known Activations