© 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 - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 13138
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to systems, controls, and performance metrics

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

    This neuron detects text describing features, qualities, or characteristics, particularly when explaining how something works or what makes it special.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    ChildScrollView
    -0.69
    Moreover
    -0.63
     Moreover
    -0.60
     Nowadays
    -0.60
    Nowadays
    -0.57
     nowadays
    -0.55
     shrimps
    -0.49
     respectivas
    -0.48
     useStyles
    -0.47
     freezed
    -0.47
    POSITIVE LOGITS
     preventative
    0.78
    Datuak
    0.73
    checkFor
    0.68
     ddelwed
    0.64
     interpretive
    0.64
    Relationships
    0.61
    agerie
    0.61
     gleaned
    0.60
     leapt
    0.60
    餵
    0.59
    Activations Density 11.816%

    No Known Activations