© 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. 13554
    Prev
    Next
    INDEX
    Explanations

    references to reporting or investigating in scientific studies

    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
    Personensuche
    -1.07
    bootstrapcdn
    -1.02
     typelib
    -0.95
    OGND
    -0.94
    AndEndTag
    -0.93
    ThroughAttribute
    -0.91
    WriteBarrier
    -0.90
    mybatisplus
    -0.89
    ViewFeatures
    -0.88
    хьтан
    -0.86
    POSITIVE LOGITS
     a
    0.62
     
    0.62
     an
    0.50
    couverte
    0.48
     mengenai
    0.45
     tiden
    0.45
     lenne
    0.43
     devenir
    0.43
     handelt
    0.43
     wzi
    0.43
    Activations Density 0.949%

    No Known Activations