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-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 13663
    Prev
    Next
    INDEX
    Explanations

    references to specific characters, particularly related to shows or narratives involving Dinah and Cassidy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     
    -0.59
     p
    -0.56
     J
    -0.56
     k
    -0.54
     \
    -0.54
    !*\
    -0.54
     ро
    -0.53
     n
    -0.53
     r
    -0.52
    istoitu
    -0.52
    POSITIVE LOGITS
     myſelf
    1.33
     themſelves
    1.32
     pleaſure
    1.31
     itſelf
    1.28
     becauſe
    1.25
     Theſe
    1.24
     Reſ
    1.23
     Efq
    1.23
     himſelf
    1.20
     whoſe
    1.20
    Activations Density 1.870%

    No Known Activations