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. 13682
    Prev
    Next
    INDEX
    Explanations

    descriptions of sports team performances and match results.

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @bot

    references to sports teams and their performances in competitions.

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    information related to sports events and team performances.

    oai_token-act-pair · gpt-3.5-turboTriggered 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
     متعلقه
    -0.70
    maxAge
    -0.58
    ornos
    -0.56
    ItemBackground
    -0.55
     getItemCount
    -0.54
     uuidv
    -0.53
    neux
    -0.51
     modelled
    -0.51
     random
    -0.50
    ialog
    -0.50
    POSITIVE LOGITS
     scored
    0.69
     scoring
    0.65
     playoffs
    0.64
     scorer
    0.62
     offensively
    0.60
    wiet
    0.57
     scorers
    0.56
     prefi
    0.56
     coached
    0.56
     scoreboard
    0.54
    Activations Density 0.068%

    No Known Activations