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-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 2011
    Prev
    Next
    INDEX
    Explanations

    legal terms and phrases related to criminal incidents and processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    DockStyle
    -0.94
    DoubleQuotes
    -0.78
    MessageTagHelper
    -0.67
    Demografía
    -0.63
     Réponses
    -0.63
     createState
    -0.62
    usermodel
    -0.59
     Theſe
    -0.58
    owol
    -0.58
    Източници
    -0.58
    POSITIVE LOGITS
     transaction
    0.89
     session
    0.88
     operation
    0.80
     sessions
    0.79
     episode
    0.78
     event
    0.76
     experiment
    0.72
     attempt
    0.71
     trip
    0.71
     transactions
    0.71
    Activations Density 1.032%

    No Known Activations