© 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. 10-GEMMASCOPE-RES-16K
    11. 4731
    Prev
    Next
    INDEX
    Explanations

    formal statements, announcements, or releases related to legal or official matters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    contentLoaded
    -0.89
     חיצוניים
    -0.83
     MonoBehaviour
    -0.77
    Personensuche
    -0.77
    +#+
    -0.77
    Билгалдахарш
    -0.74
    клопе
    -0.72
    antMatchers
    -0.72
    TagMode
    -0.70
    webElementXpaths
    -0.68
    POSITIVE LOGITS
     reads
    0.63
     listing
    0.59
     notes
    0.58
     specs
    0.55
    ódó
    0.54
     description
    0.52
    naph
    0.52
     read
    0.52
     write
    0.51
     lezen
    0.50
    Activations Density 0.285%

    No Known Activations