© 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
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 15108
    Prev
    Next
    INDEX
    Explanations

    references to expressions and their attributes within a scientific or technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    The neuron activates for the word "Expression" or similar variants like "Expressions" or "Express," particularly when referring to formal statements, declarations, or identifications.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    the word "Expression" at the beginning of sentences or headers.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    chaleco
    -0.41
    Elő
    -0.39
     pecados
    -0.39
    WaitGroup
    -0.39
     Knot
    -0.37
     auroit
    -0.37
     casó
    -0.36
     cometido
    -0.36
     houver
    -0.36
    nady
    -0.35
    POSITIVE LOGITS
     Express
    0.78
    Express
    0.75
     EXPRESS
    0.72
     expr
    0.72
     express
    0.72
     Expr
    0.71
     expres
    0.70
    EXPRESS
    0.70
    express
    0.68
     Expression
    0.67
    Activations Density 0.134%

    No Known Activations