© 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. 5794
    Prev
    Next
    INDEX
    Explanations

    references to familial relationships and dynamics

    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
    脚注の使い方
    -0.51
     AspNetCore
    -0.47
    出版年
    -0.47
     kasarigan
    -0.44
    Lähteet
    -0.40
    siel
    -0.39
    èlement
    -0.39
     препратки
    -0.39
    ibouti
    -0.38
     InputDecoration
    -0.36
    POSITIVE LOGITS
     son
    3.38
     sons
    2.75
     daughter
    2.73
     Son
    2.56
    Son
    2.41
     grandson
    2.31
     daughters
    2.23
     hijo
    2.20
     SON
    2.19
    daughter
    2.16
    Activations Density 0.831%

    No Known Activations