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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 10419
    Prev
    Next
    INDEX
    Explanations

    references to personal favorites and preferences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     destaque
    -0.57
    gaande
    -0.54
     énfasis
    -0.53
     moeite
    -0.53
     ExecuteAsync
    -0.52
    rsiniz
    -0.51
     fokus
    -0.51
     aandacht
    -0.49
     lotes
    -0.49
    mtable
    -0.49
    POSITIVE LOGITS
     movie
    1.13
     song
    1.11
     movies
    1.09
     songs
    1.00
     TV
    0.99
     foods
    0.94
     tv
    0.90
     books
    0.85
     television
    0.84
     restaurant
    0.83
    Activations Density 0.514%

    No Known Activations