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. 6535
    Prev
    Next
    INDEX
    Explanations

    references to sports statistics and performance metrics

    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
    lorette
    -0.59
     carriera
    -0.55
    DebuggerNonUser
    -0.54
    #+#
    -0.53
     Actualmente
    -0.52
     карьер
    -0.52
     Current
    -0.52
     radix
    -0.51
    umptive
    -0.51
     oaths
    -0.50
    POSITIVE LOGITS
     offensively
    0.81
     defensively
    0.78
     offense
    0.68
     defense
    0.66
    NOPQRST
    0.65
     चीज़ों
    0.65
     against
    0.63
    前半
    0.63
     Offen
    0.62
    SuppressMessage
    0.61
    Activations Density 0.212%

    No Known Activations