Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 1108
    Prev
    Next
    INDEX
    Explanations

    details related to property measurements and zoning regulations

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

    numerical measurements and dimensions of properties or physical spaces.

    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
     blé
    -0.38
     Bridges
    -0.36
     bridges
    -0.35
     Balancing
    -0.35
     pama
    -0.34
    BASEPATH
    -0.34
     puente
    -0.34
    橋
    -0.34
     Bridge
    -0.34
     ThemeData
    -0.33
    POSITIVE LOGITS
     plot
    0.84
     backyard
    0.75
     parcela
    0.72
    httphttps
    0.70
     yard
    0.69
     lot
    0.68
     Plot
    0.68
    Plot
    0.68
     plots
    0.68
     parcel
    0.66
    Activations Density 0.090%

    No Known Activations