© 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-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 2145
    Prev
    Next
    INDEX
    Explanations

    mechanical specifications and performance metrics related to vehicles

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

    Speeds, especially related to vehicles or exports

    np_acts-logits-general · gemini-2.0-flash

    reach speeds

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mergeFrom
    -0.53
    UnusedPrivate
    -0.49
    principalColumn
    -0.46
    parseFrom
    -0.45
    Архівовано
    -0.44
    Sucesor
    -0.44
     فريبيس
    -0.44
     junior
    -0.43
     Référence
    -0.42
    mergeFrom
    -0.41
    POSITIVE LOGITS
     speed
    1.78
     speeds
    1.68
    speed
    1.57
     Speeds
    1.50
     Speed
    1.47
    Speed
    1.46
     vitesse
    1.41
     SPEED
    1.39
     speeding
    1.35
    peed
    1.33
    Activations Density 0.133%

    No Known Activations