Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 41-GEMMASCOPE-RES-16K
    6. 7195
    Prev
    Next
    INDEX
    Explanations

    concepts related to programming errors or issues in code execution

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    !*\
    -0.46
    ритори
    -0.40
    eders
    -0.36
     vectoriales
    -0.34
    edom
    -0.33
     Савезне
    -0.33
    illett
    -0.32
     AssemblyProduct
    -0.31
    nesty
    -0.31
    quea
    -0.31
    POSITIVE LOGITS
     é
    1.19
     tem
    1.00
     pode
    0.93
     vai
    0.78
     faz
    0.70
     garante
    0.68
     vem
    0.67
     leva
    0.65
     deve
    0.64
     fica
    0.62
    Activations Density 0.098%

    No Known Activations