© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 9856
    Prev
    Next
    INDEX
    Explanations

    geographic locations and distances

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

    numerical distances and measurements (miles, kilometers) in geographical descriptions.

    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
     vecind
    -0.46
     cortesía
    -0.40
     tangan
    -0.39
     flotante
    -0.38
     sandalias
    -0.38
     escaleras
    -0.37
     curiosidad
    -0.36
     paciencia
    -0.35
     Relaciones
    -0.35
     llavero
    -0.34
    POSITIVE LOGITS
     miles
    1.04
    miles
    0.96
    Miles
    0.94
     km
    0.89
     MILES
    0.89
     Miles
    0.85
     kilometres
    0.79
     kilometers
    0.78
    km
    0.77
     kms
    0.76
    Activations Density 0.141%

    No Known Activations