Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 114497
    Prev
    Next
    INDEX
    Explanations

    numeric data, specifically dates and measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ſicht
    -0.85
    ſſung
    -0.84
     geſch
    -0.83
     ſeinem
    -0.82
    iſchen
    -0.81
    ロウィン
    -0.81
     erſt
    -0.80
    iſche
    -0.80
     ſind
    -0.79
    niſſe
    -0.79
    POSITIVE LOGITS
     so
    0.26
     issued
    0.24
     se
    0.24
     آمد
    0.23
     land
    0.22
     spezif
    0.22
     que
    0.21
     mis
    0.21
     born
    0.20
     m
    0.20
    Activations Density 0.152%

    No Known Activations