© 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. 104840
    Prev
    Next
    INDEX
    Explanations

    references to nationalities and associated identities

    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
    UnusedPrivate
    -0.61
    endphp
    -0.51
     Build
    -0.51
     defStyleAttr
    -0.49
     defStyle
    -0.46
    ſſion
    -0.45
     itſelf
    -0.45
     ſou
    -0.44
     faſt
    -0.44
     leſs
    -0.44
    POSITIVE LOGITS
    DebuggerStep
    0.42
    ctin
    0.40
    amilya
    0.38
     rival
    0.37
    rentina
    0.37
    いずれ
    0.37
     größ
    0.36
    iotensin
    0.35
     competitors
    0.35
     competitor
    0.34
    Activations Density 0.006%

    No Known Activations