© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 14724
    Prev
    Next
    INDEX
    Explanations

    No clear pattern is discernible because the neuron never activates on the provided text, so its feature is undetermined from these examples.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    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
     fhew
    -0.60
    principalColumn
    -0.60
     kasarigan
    -0.59
    RefNanny
    -0.59
     purpoſe
    -0.57
     Anſ
    -0.56
     anſ
    -0.52
    Personensuche
    -0.52
     InputDecoration
    -0.52
     civilisation
    -0.52
    POSITIVE LOGITS
     written
    0.45
    不禁
    0.38
     surla
    0.36
     pyplot
    0.36
     Италијани
    0.34
    CardModule
    0.32
    (`
    0.31
    statechange
    0.31
     geschrieben
    0.30
     verhe
    0.30
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.