© 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. 0-GEMMASCOPE-RES-16K
    11. 9451
    Prev
    Next
    INDEX
    Explanations

    phrases or clauses that contain the word "that" indicating a specific relationship or consequence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    protoimpl
    -0.64
    AnimationsModule
    -0.62
    VIAF
    -0.58
    Tikang
    -0.55
     CanadaChoose
    -0.51
     the
    -0.51
    pulumi
    -0.50
     mouseClicked
    -0.50
    җ
    -0.49
    出版年
    -0.48
    POSITIVE LOGITS
     فريبيس
    0.44
     ligiloj
    0.43
    erweise
    0.34
    ingly
    0.33
     població
    0.32
    égard
    0.31
    miljø
    0.31
     jemand
    0.31
    plish
    0.31
     kwamba
    0.31
    Activations Density 0.371%

    No Known Activations