© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 14048
    Prev
    Next
    INDEX
    Explanations

    references to legal cases and their associated details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/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.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     veau
    -0.31
    Mutagenicity
    -0.29
     circon
    -0.29
    kháu
    -0.28
     незавершена
    -0.28
    闹
    -0.27
     réglable
    -0.27
    aktur
    -0.27
     raffredd
    -0.27
    ituary
    -0.27
    POSITIVE LOGITS
     merged
    2.17
     merging
    2.11
     merge
    2.03
     merger
    1.93
    合并
    1.85
     amalgam
    1.85
     merges
    1.85
     combined
    1.80
     fusion
    1.77
     combine
    1.76
    Activations Density 1.549%

    No Known Activations