© 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-2-9B
    7. Residual Stream - 16k
    9. 37-GEMMASCOPE-RES-16K
    11. 3959
    Prev
    Next
    INDEX
    Explanations

    Chinese characters and specific word forms in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ThroughAttribute
    -0.56
    hésite
    -0.41
    StoryboardSegue
    -0.39
    XmlEnum
    -0.37
    下来
    -0.37
     Putih
    -0.36
    httphttps
    -0.35
    Izvori
    -0.35
     communiquez
    -0.35
    getreten
    -0.35
    POSITIVE LOGITS
    colgroup
    0.55
    PDOException
    0.51
     bangs
    0.50
     lod
    0.46
    +```
    0.43
    CPtr
    0.43
    EndInit
    0.42
    〮
    0.42
     Stock
    0.41
    cension
    0.41
    Activations Density 0.094%

    No Known Activations