© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 941
    Prev
    Next
    INDEX
    Explanations

    references to historical or biographical information related to individuals, including dates and significant events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     verv
    -0.38
    嘴
    -0.38
    EROS
    -0.37
     kasarigan
    -0.36
     zel
    -0.36
    anging
    -0.35
     standard
    -0.34
     Vlad
    -0.34
    IsContent
    -0.34
     technological
    -0.34
    POSITIVE LOGITS
    StoryboardSegue
    0.88
     surla
    0.72
     funerals
    0.62
     betweenstory
    0.61
    ituaries
    0.60
     fallecido
    0.60
    deceased
    0.58
     funeral
    0.57
     resultCode
    0.57
     obituary
    0.56
    Activations Density 0.040%

    No Known Activations