© 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. 7-GEMMASCOPE-RES-16K
    11. 16328
    Prev
    Next
    INDEX
    Explanations

    phrases indicating establishment or recognition of status and position

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     propOrder
    -0.51
     chain
    -0.37
     Release
    -0.36
     Grady
    -0.35
     Holtz
    -0.35
     Chain
    -0.34
     MatDialog
    -0.34
     ur
    -0.34
     Conversion
    -0.32
     Ster
    -0.32
    POSITIVE LOGITS
     dominance
    0.63
     prominence
    0.62
    inence
    0.59
     popularity
    0.57
     myſelf
    0.57
     otomatig
    0.55
    すっかり
    0.54
    levance
    0.54
    ſelf
    0.54
     popularidad
    0.53
    Activations Density 0.438%

    No Known Activations