© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 103519
    Prev
    Next
    INDEX
    Explanations

    concepts related to statistical measurements and counterfactuals

    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
    PMailer
    -0.61
    исленность
    -0.60
     AspNetCore
    -0.56
    featureID
    -0.56
     $_"
    -0.56
    principalColumn
    -0.56
    Personendaten
    -0.54
    AxisAlignment
    -0.53
     houſe
    -0.53
    esModule
    -0.53
    POSITIVE LOGITS
     contexts
    0.48
     context
    0.39
     readers
    0.36
     cognitive
    0.34
     contextos
    0.32
    帖最后由
    0.31
     constituting
    0.31
     ロール
    0.31
     characterized
    0.30
    unun
    0.30
    Activations Density 0.058%

    No Known Activations