© 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. 3-GEMMASCOPE-RES-16K
    11. 5667
    Prev
    Next
    INDEX
    Explanations

    references to callback functions in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Хьажоргаш
    -0.54
     gynhyrchwyd
    -0.50
     مشين
    -0.50
    expandindo
    -0.48
    openConnection
    -0.48
    ftagPool
    -0.46
     pression
    -0.46
     '\\;'
    -0.46
     ostavi
    -0.45
     ivelany
    -0.45
    POSITIVE LOGITS
     Cambridge
    0.81
    Callback
    0.77
     callback
    0.75
    Cambridge
    0.73
     Callback
    0.67
     callbacks
    0.66
    cb
    0.65
    callback
    0.64
    CALLBACK
    0.63
     cb
    0.60
    Activations Density 0.077%

    No Known Activations