© 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. 8-GEMMASCOPE-RES-16K
    11. 3397
    Prev
    Next
    INDEX
    Explanations

    document structure markers or metadata

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    存于互联网档案馆
    -0.67
    CLUS
    -0.59
     continuant
    -0.57
     lumen
    -0.56
    Bronnen
    -0.55
    stretchr
    -0.54
     fibrillation
    -0.53
    MISSION
    -0.52
    RUNTIME
    -0.52
     hypoch
    -0.52
    POSITIVE LOGITS
    <bos>
    1.11
     thiệu
    0.61
    ècie
    0.61
    Portail
    0.60
    __":
    0.56
     }}"></
    0.55
     '\\;'
    0.55
    tonode
    0.54
     needed
    0.54
     Waray
    0.52
    Activations Density 3.614%

    No Known Activations