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. 0-GEMMASCOPE-RES-16K
    6. 6542
    Prev
    Next
    INDEX
    Explanations

    the concept of blessings and their significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Jefus
    -1.42
    ſelves
    -1.42
     itſelf
    -1.41
     themſelves
    -1.36
     myſelf
    -1.35
     himſelf
    -1.34
     raiſ
    -1.33
    ſelf
    -1.32
     purpoſe
    -1.31
     ſeveral
    -1.29
    POSITIVE LOGITS
     blessing
    0.84
     bless
    0.81
    bless
    0.72
     icon
    0.68
    Bless
    0.65
    cz
    0.65
     blessings
    0.62
    HtmlAttribute
    0.61
    icon
    0.60
     Ven
    0.60
    Activations Density 0.082%

    No Known Activations