© 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. 7-GEMMASCOPE-RES-16K
    11. 13725
    Prev
    Next
    INDEX
    Explanations

    terms related to medical procedures and conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     '\\;'
    -0.39
     esponja
    -0.38
    ografija
    -0.36
     figliu
    -0.35
     inoxidable
    -0.35
     ensamb
    -0.33
    LEGGI
    -0.33
     matériaux
    -0.32
     perdon
    -0.32
     productivo
    -0.32
    POSITIVE LOGITS
     ingame
    0.78
     onsite
    0.77
     intracellular
    0.75
     onscreen
    0.71
    Intra
    0.65
     Intra
    0.64
     inline
    0.63
    locally
    0.60
     onboard
    0.60
     intra
    0.60
    Activations Density 0.878%

    No Known Activations