© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 105901
    Prev
    Next
    INDEX
    Explanations

    statements affirming or describing the quality of something, particularly using variations of the verb "to be" and clusters of descriptive phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
     xPos
    -0.45
     mogelijkheden
    -0.44
    msgTypes
    -0.43
    InstrumentedTest
    -0.43
     défa
    -0.40
    -------
    -0.40
     enfans
    -0.39
     guerrero
    -0.39
     planche
    -0.39
     vache
    -0.39
    POSITIVE LOGITS
    Это
    0.73
     Это
    0.70
     is
    0.67
     }}=
    0.63
    это
    0.62
    ]]=
    0.59
     }=
    0.57
    ίναι
    0.57
     a
    0.57
    のは
    0.56
    Activations Density 0.008%

    No Known Activations