© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 3193
    Prev
    Next
    INDEX
    Explanations

    occurrences of the keyword "init" in code, suggesting it is focused on initialization methods in classes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Pomer
    -0.45
     Boring
    -0.41
     infla
    -0.41
     dancing
    -0.40
     Dancers
    -0.39
     surla
    -0.39
     Slowly
    -0.39
    slowly
    -0.38
    istolet
    -0.38
    Slowly
    -0.38
    POSITIVE LOGITS
     initiated
    1.02
     initiate
    0.94
    initiated
    0.92
     initiation
    0.90
     Initiate
    0.83
     initiating
    0.81
    init
    0.80
     INITI
    0.80
     initiates
    0.79
     oral
    0.78
    Activations Density 0.158%

    No Known Activations