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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 9243
    Prev
    Next
    INDEX
    Explanations

    information related to concerts and ticket sales

    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
     LEADER
    -0.56
     Kompon
    -0.51
     pinulongan
    -0.50
    namon
    -0.50
    voiced
    -0.49
    úb
    -0.49
     composers
    -0.48
     Composer
    -0.47
    +#+#
    -0.47
    atzung
    -0.46
    POSITIVE LOGITS
     tour
    1.03
     touring
    0.99
     tournée
    0.95
     concert
    0.88
    tour
    0.87
     toured
    0.86
     gigs
    0.86
    ########.
    0.86
     tours
    0.84
    Tour
    0.84
    Activations Density 0.104%

    No Known Activations