© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 126042
    Prev
    Next
    INDEX
    Explanations

    phrases related to significant concepts or themes in academic and formal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    Tembelea
    -0.75
    majánló
    -0.66
    verwijspagina
    -0.65
     useAppContext
    -0.65
    PerformLayout
    -0.63
     témoig
    -0.63
    bootstrapcdn
    -0.63
     Signalez
    -0.62
    ロウィン
    -0.60
    enderror
    -0.60
    POSITIVE LOGITS
    ArrowToggle
    0.38
    endregion
    0.35
     autorytatywna
    0.34
    Ver
    0.31
    nodoc
    0.31
    Wondering
    0.30
    VersionUID
    0.30
    Indeed
    0.29
     zun
    0.29
     
    0.29
    Activations Density 0.147%

    No Known Activations