© 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. 40-GEMMASCOPE-RES-16K
    6. 2193
    Prev
    Next
    INDEX
    Explanations

    numerical data, particularly in the context of statistics or measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    httphttps
    -0.97
    <?
    -0.82
    /*
    -0.82
    MessageTagHelper
    -0.76
    /**
    -0.76
     <<<<<<<<<<<<<<
    -0.73
     تضيفلها
    -0.71
    queryInterface
    -0.70
    endphp
    -0.70
     surla
    -0.69
    POSITIVE LOGITS
     veckor
    0.42
     américains
    0.38
     pisau
    0.37
     istrinya
    0.36
     cromado
    0.36
     trasero
    0.36
     tercero
    0.35
     quatre
    0.35
     tunggal
    0.35
     héroe
    0.35
    Activations Density 0.649%

    No Known Activations