© 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. 14-GEMMASCOPE-RES-16K
    11. 9087
    Prev
    Next
    INDEX
    Explanations

    narratives and storytelling elements, particularly focusing on accounts of life experiences and historical tales

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kasarigan
    -0.66
     שוליים
    -0.57
    AddHtmlAttribute
    -0.57
     GenerationType
    -0.56
    iſen
    -0.55
    iffion
    -0.55
    UIControlState
    -0.55
     $_(
    -0.54
    ponses
    -0.54
    AutoScaleMode
    -0.53
    POSITIVE LOGITS
     story
    1.02
     stories
    0.91
    story
    0.82
    故事
    0.77
     tale
    0.76
     tales
    0.75
     historias
    0.74
     narrative
    0.73
     narrated
    0.73
     STORY
    0.72
    Activations Density 0.435%

    No Known Activations