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 - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 117398
    Prev
    Next
    INDEX
    Explanations

    sequences of letters or specific combinations in a probabilistic context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
    Билгалдахарш
    -0.83
    хьтан
    -0.73
    ſelf
    -0.71
    MLLoader
    -0.71
     Houſe
    -0.68
     kasarigan
    -0.68
    AddTagHelper
    -0.67
     nakalista
    -0.67
     ſta
    -0.66
     myſelf
    -0.66
    POSITIVE LOGITS
     Night
    0.36
    im
    0.33
    -
    0.32
     Weather
    0.31
    ↵↵
    0.31
    star
    0.31
     cháy
    0.31
     
    0.31
     night
    0.30
     stars
    0.30
    Activations Density 0.108%

    No Known Activations