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. 1352
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate quantity or abundance

    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
    othermal
    -0.52
     proble
    -0.49
     peper
    -0.49
    Rast
    -0.48
     bres
    -0.47
     Salto
    -0.47
     reserved
    -0.47
     betweenstory
    -0.47
     hus
    -0.46
     probleme
    -0.46
    POSITIVE LOGITS
    Datuak
    0.90
    NameInMap
    0.88
    +#+
    0.86
    MessageOf
    0.86
    Enllaces
    0.79
     AssemblyCompany
    0.76
    featureID
    0.76
    Portail
    0.75
    InjectAttribute
    0.75
     nonatomic
    0.73
    Activations Density 0.087%

    No Known Activations