© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 10812
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals or entities

    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
     Trasp
    -0.62
     Maw
    -0.60
     Castor
    -0.60
     ❖
    -0.59
     Baum
    -0.59
     aset
    -0.58
     Baillargeon
    -0.56
    feeder
    -0.56
     Bate
    -0.55
    ❖
    -0.55
    POSITIVE LOGITS
     Soo
    0.99
    sizeCache
    0.92
     متعلقه
    0.85
    Soo
    0.85
     figliu
    0.84
     daqui
    0.81
     Fuhr
    0.81
     tatuagens
    0.80
     GoogleFonts
    0.79
    الحياه
    0.79
    Activations Density 2.468%

    No Known Activations