© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 4034
    Prev
    Next
    INDEX
    Explanations

    specific scientific techniques and measurements related to laboratory procedures

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

    Lab instruments or kits

    np_acts-logits-general · gemini-2.0-flash

    commercial kits and analyzers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    әрмәләр
    -0.64
     المعيارى
    -0.60
     незавершена
    -0.56
    +#+#
    -0.56
     BoxFit
    -0.56
     queſta
    -0.55
     AssemblyTitle
    -0.53
    niająca
    -0.52
    verwijspagina
    -0.51
     חיצוניים
    -0.51
    POSITIVE LOGITS
     comercial
    0.36
     commercial
    0.35
     estándares
    0.33
    Biographie
    0.33
    Catalogue
    0.32
     fue
    0.32
     맞
    0.32
     hemsida
    0.32
     tacto
    0.32
     flota
    0.31
    Activations Density 1.786%

    No Known Activations