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. 114648
    Prev
    Next
    INDEX
    Explanations

    aspects related to legal communications and stipulations

    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
     consommate
    -0.48
     Gallimard
    -0.48
     NavController
    -0.40
     auroit
    -0.39
     SqlCommand
    -0.39
     étrang
    -0.39
     Sénat
    -0.39
    cookieParser
    -0.38
     Consumer
    -0.38
     CONSUM
    -0.38
    POSITIVE LOGITS
    transQ
    0.70
    labus
    0.51
     defStyleAttr
    0.49
    IndentedString
    0.47
     propOrder
    0.42
     "
    0.42
     <<<<<<<<<<<<<<
    0.42
     "...
    0.41
     ``
    0.41
     InputDecoration
    0.41
    Activations Density 0.150%

    No Known Activations