© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 12417
    Prev
    Next
    INDEX
    Explanations

    topics related to celebrity lifestyles and personal milestones

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    references to luxury real estate and high-value properties.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     idéia
    -0.99
     läßt
    -0.83
     muß
    -0.82
     daß
    -0.80
    faßt
    -0.72
    wußt
    -0.71
     Moslem
    -0.70
     skall
    -0.69
     Schluß
    -0.67
     Daß
    -0.67
    POSITIVE LOGITS
     reportedly
    0.90
     ⁠
    0.87
     ​​
    0.80
    ⁠
    0.75
     Notably
    0.72
    ​​​​​​​
    0.68
     alongside
    0.66
    Alongside
    0.66
    ​​​​
    0.65
     demnach
    0.65
    Activations Density 0.515%

    No Known Activations