© 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. 20-GEMMASCOPE-RES-16K
    11. 12643
    Prev
    Next
    INDEX
    Explanations

    affirmations or agreements in conversation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    بوابة
    -0.66
    ruik
    -0.63
    :✨
    -0.60
    󠁢
    -0.60
     estekak
    -0.60
     queſta
    -0.60
     հղումներ
    -0.59
    Geplaatst
    -0.59
    ImageContext
    -0.58
     ſind
    -0.57
    POSITIVE LOGITS
    oredCriteria
    0.40
     nods
    0.38
     enamorado
    0.36
     الحره
    0.35
     buena
    0.34
     nonatomic
    0.33
     istrinya
    0.33
     nodded
    0.33
     provisoire
    0.32
     buona
    0.31
    Activations Density 0.104%

    No Known Activations