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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 12735
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to cloud computing and data centers

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

    Cloud computing and data centers

    np_acts-logits-general · gemini-2.0-flash

    cloud hosting data center

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    Portail
    -0.66
    Demografia
    -0.65
     يتيمه
    -0.61
    ✨:
    -0.60
     typelib
    -0.60
     Pistol
    -0.59
    haru
    -0.56
    },[])
    -0.55
    Спасылкі
    -0.55
    MLLoader
    -0.54
    POSITIVE LOGITS
     cloud
    1.40
     Cloud
    1.25
    Cloud
    1.16
    cloud
    1.15
     datac
    1.09
     CLOUD
    1.02
     clouds
    1.00
    CLOUD
    0.90
     hosting
    0.88
     hosted
    0.87
    Activations Density 0.243%

    No Known Activations