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. 5-GEMMASCOPE-RES-16K
    6. 16362
    Prev
    Next
    INDEX
    Explanations

    legal disputes and references to contests or challenges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    synap
    -0.76
    vrons
    -0.69
    Uhm
    -0.69
    pecha
    -0.68
    haja
    -0.68
    loadMore
    -0.65
    PSK
    -0.64
    DataBean
    -0.63
    ofsky
    -0.63
     MUM
    -0.63
    POSITIVE LOGITS
     CONTEST
    1.09
     Cont
    1.03
    Cont
    0.98
     Contest
    0.95
    Contest
    0.90
     Runner
    0.89
    contest
    0.88
     contested
    0.87
     runner
    0.86
     contests
    0.85
    Activations Density 0.152%

    No Known Activations