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

    Neuronpedia

    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. 40-GEMMASCOPE-RES-16K
    11. 2655
    Prev
    Next
    INDEX
    Explanations

    specific names and titles related to events, people, or places

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kasarigan
    -0.65
    UserScript
    -0.56
    elemField
    -0.55
    出版年
    -0.54
     disambiguazione
    -0.53
    elfth
    -0.52
     NSCoder
    -0.51
     useAppContext
    -0.50
     GenerationType
    -0.50
    eqn
    -0.50
    POSITIVE LOGITS
    InputModule
    0.42
    ButtonModule
    0.36
     abandonado
    0.34
     interesantes
    0.34
    ACHUSETTS
    0.32
    IconModule
    0.32
     ipsum
    0.30
    tadır
    0.29
    RICAL
    0.28
     repuesto
    0.28
    Activations Density 0.395%

    No Known Activations