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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 6850
    Prev
    Next
    INDEX
    Explanations

    instances of the word "excess" in various contexts

    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
    transQ
    -0.47
     kaarangay
    -0.43
     mérite
    -0.42
    istán
    -0.40
    ïsme
    -0.40
     éto
    -0.39
     battles
    -0.39
     gravedad
    -0.39
     financieras
    -0.39
     aids
    -0.38
    POSITIVE LOGITS
     surplus
    1.80
     excess
    1.78
    Excess
    1.68
     Excess
    1.64
    excess
    1.62
     Surplus
    1.46
     spare
    1.11
     surpluses
    1.09
     unused
    0.99
    spare
    0.98
    Activations Density 0.087%

    No Known Activations