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. 5-GEMMASCOPE-RES-16K
    6. 1889
    Prev
    Next
    INDEX
    Explanations

    instances of the word "even" and variations of it in different contexts, along with their associated actions or sentiments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AppColors
    -0.74
    /*
    -0.71
    MessageTagHelper
    -0.66
     cuire
    -0.64
     ashore
    -0.64
     SwitchCompat
    -0.64
     Aws
    -0.63
     TextInputType
    -0.63
    Continua
    -0.61
     cref
    -0.61
    POSITIVE LOGITS
     even
    1.13
    even
    0.92
     sogar
    0.92
     Even
    0.90
    Even
    0.86
     EVEN
    0.80
     даже
    0.77
     persino
    0.77
     incluso
    0.76
    Incluso
    0.73
    Activations Density 0.126%

    No Known Activations