© 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. 4288
    Prev
    Next
    INDEX
    Explanations

    references to observable patterns or attributes in data structures

    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
    StoryboardSegue
    -0.69
     متعلقه
    -0.66
    twimg
    -0.60
    InstrumentedTest
    -0.59
    ativis
    -0.59
    RRect
    -0.58
     ostavi
    -0.57
     Sodom
    -0.57
    Accessors
    -0.56
    xsi
    -0.56
    POSITIVE LOGITS
     useState
    4.07
    useState
    3.50
     useRef
    0.94
     StatefulWidget
    0.80
     useDispatch
    0.79
     useEffect
    0.77
     useCallback
    0.74
    المراجع
    0.70
     useParams
    0.66
     useRouter
    0.66
    Activations Density 0.006%

    No Known Activations