© 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 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. 15772
    Prev
    Next
    INDEX
    Explanations

    keywords related to automotive design and features

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

    Describing a vehicle's visual appearance

    np_acts-logits-general · gemini-2.0-flash

    visual appearance and design

    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
     الحره
    -0.63
     protoimpl
    -0.62
     Sénat
    -0.56
    Rhestr
    -0.55
     XCTest
    -0.55
     friable
    -0.54
     vetorial
    -0.54
     referrerpolicy
    -0.53
     SafeMath
    -0.53
    LLocation
    -0.53
    POSITIVE LOGITS
     aesthetically
    1.33
     aesthetics
    1.31
     aesthetic
    1.30
     appearance
    1.15
     looks
    1.14
     estética
    1.10
     stylish
    1.06
     look
    1.06
     design
    1.05
     Aesthetic
    1.05
    Activations Density 0.205%

    No Known Activations