© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 37-GEMMASCOPE-RES-16K
    6. 5503
    Prev
    Next
    INDEX
    Explanations

    conditional statements and main function calls in a programming context

    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
    SequentialGroup
    -0.48
    preuves
    -0.37
    êmes
    -0.35
    HasBeenSet
    -0.35
     impresora
    -0.33
    __()
    -0.32
     impuesto
    -0.32
     laikā
    -0.32
     jScrollPane
    -0.31
    imwrite
    -0.31
    POSITIVE LOGITS
    ंदीखरीदारी
    0.66
    (__
    0.57
     betweenstory
    0.53
    CloseOperation
    0.52
     ujednoznacz
    0.52
    Far
    0.51
     Waray
    0.51
     вікісторінку
    0.48
     __
    0.48
    iddhar
    0.48
    Activations Density 0.358%

    No Known Activations