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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 2595
    Prev
    Next
    INDEX
    Explanations

    keywords and phrases related to automobiles and vehicles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ddots
    -0.54
    LayoutStyle
    -0.54
    XmlAccessType
    -0.53
     distanciation
    -0.52
     planches
    -0.52
     olympique
    -0.52
     navires
    -0.49
     leiden
    -0.49
     }}}
    -0.48
    peq
    -0.48
    POSITIVE LOGITS
     cars
    1.37
     vehicles
    1.36
     vehicle
    1.33
     automobile
    1.28
     Vehicles
    1.27
     automobiles
    1.25
     car
    1.21
     Cars
    1.21
     motorist
    1.20
     Vehicle
    1.20
    Activations Density 0.281%

    No Known Activations