© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 30-GEMMASCOPE-RES-16K
    6. 10531
    Prev
    Next
    INDEX
    Explanations

    references to geographic locations and their distance from major cities or landmarks

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

    Distance or time measurement

    np_acts-logits-general · gemini-2.0-flash

    hour drive

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    出版年
    -0.61
    rungsseite
    -0.52
    ThemeOverlay
    -0.48
     Photocase
    -0.46
    __((
    -0.45
     escaleras
    -0.45
     esquina
    -0.44
    DMETHOD
    -0.43
    ="@+
    -0.43
     sidewalks
    -0.43
    POSITIVE LOGITS
     drive
    0.80
    Drive
    0.74
     driving
    0.73
    driving
    0.73
     Driving
    0.72
    Driving
    0.71
    drive
    0.70
     Drive
    0.69
     hour
    0.64
     drove
    0.63
    Activations Density 0.159%

    No Known Activations