© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 863
    Prev
    Next
    INDEX
    Explanations

    elements related to nostalgia and retro themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     raiſ
    -0.92
     Efq
    -0.87
    esgue
    -0.85
     myſelf
    -0.84
     ſeveral
    -0.83
     itſelf
    -0.82
    Искәрмәләр
    -0.82
     ſever
    -0.81
     reaſon
    -0.81
     deſt
    -0.80
    POSITIVE LOGITS
     nostalgia
    1.42
     nostalgic
    1.40
     retro
    1.32
     nostal
    1.32
    retro
    1.26
     throwback
    1.23
    Retro
    1.21
     vintage
    1.20
     Retro
    1.20
     Nostalgia
    1.17
    Activations Density 0.677%

    No Known Activations