© 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. 934
    Prev
    Next
    INDEX
    Explanations

    references to programming constructs and data structures

    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
    glises
    -0.38
     krig
    -0.35
    代わりに
    -0.33
     nota
    -0.33
     rito
    -0.32
    何况
    -0.32
     millas
    -0.32
    twimg
    -0.31
    ∴
    -0.30
     ayrıca
    -0.30
    POSITIVE LOGITS
    ьаж
    0.63
    EDEFAULT
    0.62
     Normdatei
    0.59
    delwed
    0.57
    NameInMap
    0.57
     oprot
    0.57
    InputBorder
    0.55
    parsedMessage
    0.54
     fieldNum
    0.51
    webElementXpaths
    0.50
    Activations Density 0.485%

    No Known Activations