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-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 484
    Prev
    Next
    INDEX
    Explanations

    mentions of seasons, particularly summer and winter

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 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
     espelho
    -0.49
     članak
    -0.47
    sträger
    -0.44
    voerd
    -0.42
     Befehl
    -0.41
     varandra
    -0.41
     telefoon
    -0.40
     todella
    -0.40
     rispond
    -0.40
     raça
    -0.40
    POSITIVE LOGITS
    Winter
    0.91
     winter
    0.87
    WINTER
    0.86
     Winter
    0.86
     WINTER
    0.85
    Summer
    0.84
    winter
    0.80
     Winters
    0.79
    Spring
    0.78
     winters
    0.78
    Activations Density 0.086%

    No Known Activations