© 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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 82749
    Prev
    Next
    INDEX
    Explanations

    This neuron is effectively inactive — it doesn't respond to any tokens (it finds nothing).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BufferException
    -0.81
    Tembelea
    -0.77
    IsMutable
    -0.72
    AndEndTag
    -0.68
     betweenstory
    -0.68
     aanz
    -0.68
    GraphicsUnit
    -0.68
    ScopeManager
    -0.67
    Sucesor
    -0.67
    verwijspagina
    -0.67
    POSITIVE LOGITS
    self
    0.28
     acerca
    0.25
    minWidth
    0.25
    Filme
    0.25
     везе
    0.25
    何が
    0.24
     paraître
    0.24
     advertencia
    0.24
     Grüsse
    0.24
     vald
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.