© 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-2-2B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 6450
    Prev
    Next
    INDEX
    Explanations

    sentences with emotional or subjective expressions, particularly regarding opinions and personal reflections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     diatas
    -0.69
    非常的
    -0.60
     betek
    -0.57
     didalam
    -0.56
     dolayı
    -0.56
    為に
    -0.55
     כאשר
    -0.54
     ‘’
    -0.54
    ‘’
    -0.54
     данного
    -0.54
    POSITIVE LOGITS
    ].)
    0.94
     disambiguazione
    0.94
     heh
    0.79
     ostensibly
    0.76
    Искәрмәләр
    0.75
    eabouts
    0.72
    NOON
    0.71
     ―――――
    0.71
    ècie
    0.70
     lemme
    0.70
    Activations Density 0.639%

    No Known Activations