© 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-2-9B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 1503
    Prev
    Next
    INDEX
    Explanations

    elements that are striking or impactful in storytelling and memorable experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Erreferentziak
    -0.59
    Források
    -0.53
     adiv
    -0.49
    Referències
    -0.47
    Démographie
    -0.44
    scalatest
    -0.43
     rumours
    -0.43
    
    -0.42
    Schedulers
    -0.41
     speculation
    -0.40
    POSITIVE LOGITS
     memorable
    0.80
     impactful
    0.79
    impact
    0.70
     impact
    0.69
     impression
    0.68
    インパクト
    0.67
     unforgettable
    0.66
    IMPACT
    0.66
     Impression
    0.65
    Impact
    0.64
    Activations Density 0.273%

    No Known Activations