© 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. 21-GEMMASCOPE-RES-16K
    11. 8117
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to health, medicine, and usage statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nanti
    -0.63
    XDECREF
    -0.54
     dagens
    -0.54
    Eventually
    -0.54
     prochains
    -0.49
    Later
    -0.48
     Eventually
    -0.48
    prepareStatement
    -0.48
     Later
    -0.47
    Ultimately
    -0.47
    POSITIVE LOGITS
     since
    3.53
    since
    3.10
     SINCE
    2.92
     Since
    2.65
    Since
    2.62
     depuis
    2.52
     sejak
    2.39
     seit
    2.25
     fince
    2.23
     sinds
    2.13
    Activations Density 0.529%

    No Known Activations