© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 432
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize importance or significance

    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
    us
    -0.55
    R
    -0.55
     don
    -0.54
     usually
    -0.52
     -
    -0.52
    ↵
    -0.51
     often
    -0.51
     اغ
    -0.50
     [
    -0.50
    ,
    -0.50
    POSITIVE LOGITS
     propOrder
    1.16
    WebVitals
    1.09
     PLWABN
    1.02
    NameInMap
    1.02
     EconPapers
    1.01
    GOTREF
    1.01
     Theſe
    1.01
     ainfi
    1.00
     GenerationType
    1.00
     avoient
    0.99
    Activations Density 0.054%

    No Known Activations