© 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 EvalsExportsinterp-engineNEWAPI 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. 102206
    Prev
    Next
    INDEX
    Explanations

    punctuation and sentence-ending structures

    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
    Rüyada
    -0.60
     BoxFit
    -0.52
     ennen
    -0.51
    glement
    -0.45
     ContentValues
    -0.45
    ipts
    -0.43
     Feedback
    -0.43
     gyhoeddwyd
    -0.42
     FEEDBACK
    -0.41
    tonsoft
    -0.40
    POSITIVE LOGITS
    Билгалдахарш
    0.47
     sumpay
    0.46
    posedge
    0.43
    FDRE
    0.42
    abetes
    0.42
    RegressionTest
    0.42
     PeEnEo
    0.42
     contextLoads
    0.41
    Personensuche
    0.40
     iParam
    0.39
    Activations Density 0.085%

    No Known Activations