© 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. 10-GEMMASCOPE-RES-16K
    11. 6169
    Prev
    Next
    INDEX
    Explanations

    indicators of structured data types or specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Etc
    -0.41
     terk
    -0.36
    Etc
    -0.35
    eraard
    -0.32
     newVal
    -0.32
    廉
    -0.32
     mutate
    -0.32
     rc
    -0.31
    aryngeal
    -0.30
     Rc
    -0.30
    POSITIVE LOGITS
    StructEnd
    0.59
    writeFieldEnd
    0.59
    ValueStyle
    0.58
     Савезне
    0.57
     OFDb
    0.56
    ariConfig
    0.52
     autorytatywna
    0.52
     FetchType
    0.51
    errHandler
    0.51
    期刊论文
    0.50
    Activations Density 0.943%

    No Known Activations