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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 7306
    Prev
    Next
    INDEX
    Explanations

    references to weather phenomena and conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ThroughAttribute
    -0.85
    LEncoder
    -0.77
    PerformLayout
    -0.76
     otomatig
    -0.74
     AssemblyCulture
    -0.74
    GraphicsUnit
    -0.72
    
    -0.72
    RenderAtEndOf
    -0.71
    IsContent
    -0.69
     onOptions
    -0.68
    POSITIVE LOGITS
     temperature
    0.94
    Temperature
    0.84
     Temperature
    0.84
     temperatures
    0.82
    temperature
    0.82
     temperatura
    0.78
     Temperatures
    0.77
     thermometer
    0.74
     temp
    0.73
     température
    0.73
    Activations Density 0.107%

    No Known Activations