© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 105461
    Prev
    Next
    INDEX
    Explanations

    mentions of social media platforms and their associated activities

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    AddTagHelper
    -0.51
    AISSEE
    -0.48
    gever
    -0.45
    basicConfig
    -0.44
    mantec
    -0.43
    RegressionTest
    -0.43
    Sail
    -0.42
     siff
    -0.42
    机制
    -0.42
    charest
    -0.41
    POSITIVE LOGITS
     ligiloj
    0.45
    featureID
    0.44
     dAtA
    0.42
    ArgsConstructor
    0.39
    RegistryLite
    0.38
    itschrift
    0.37
    הערות
    0.37
    脚注の使い方
    0.36
     يتيمه
    0.36
     koordin
    0.35
    Activations Density 0.006%

    No Known Activations