© 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. 27-GEMMASCOPE-RES-16K
    11. 9879
    Prev
    Next
    INDEX
    Explanations

    phrases and sentiments related to feelings of nostalgia and longing for deeper connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dets
    -0.36
    писки
    -0.36
    全く
    -0.36
    sproz
    -0.35
    //
    -0.35
    Вес
    -0.34
    currPos
    -0.34
    FixedSize
    -0.34
    的需求
    -0.34
     ecos
    -0.33
    POSITIVE LOGITS
    那種
    0.85
     aquele
    0.79
    那种
    0.78
    ⓧ
    0.76
     kind
    0.76
     aquela
    0.75
    queles
    0.73
     aqueles
    0.69
    的那种
    0.69
     type
    0.65
    Activations Density 0.247%

    No Known Activations