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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 33372
    Prev
    Next
    INDEX
    Explanations

    the occurrences of the day "Monday" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     oscuridad
    -0.45
    4
    -0.41
     aislado
    -0.40
    riturismo
    -0.40
     Privacidad
    -0.39
     olev
    -0.39
    5
    -0.39
     esternos
    -0.39
    detectChanges
    -0.39
     Jerez
    -0.38
    POSITIVE LOGITS
     Monday
    1.40
    Monday
    1.40
     MONDAY
    1.28
     monday
    1.27
     Mondays
    1.27
    monday
    1.22
    MONDAY
    1.21
    Tuesday
    1.07
     Tuesday
    1.05
     lunedì
    0.98
    Activations Density 0.004%

    No Known Activations