© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 13891
    Prev
    Next
    INDEX
    Explanations

    references to functional or operational contexts in various systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hilangan
    -0.43
     Hilfe
    -0.39
     sebaliknya
    -0.37
    Ỉ
    -0.37
     kematian
    -0.36
     regalías
    -0.36
     tamamen
    -0.35
    дожник
    -0.35
     cantidades
    -0.35
     ever
    -0.34
    POSITIVE LOGITS
     working
    1.88
     Working
    1.72
    Working
    1.68
     WORKING
    1.66
    working
    1.63
    WORKING
    1.59
     operating
    1.13
     Arbeits
    1.06
    Arbeits
    1.06
     trabajando
    1.04
    Activations Density 0.313%

    No Known Activations