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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 21-GEMMASCOPE-RES-16K
    6. 8349
    Prev
    Next
    INDEX
    Explanations

    occurrences of the date "January 9" and variations in spelling or representation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     насељу
    -0.58
     summers
    -0.56
    Попис
    -0.54
     Summer
    -0.53
    人民共和国
    -0.53
    summer
    -0.52
     summer
    -0.51
    帖最后由
    -0.51
    Summer
    -0.50
    IBarButtonItem
    -0.48
    POSITIVE LOGITS
     HasFactory
    0.79
     Ocak
    0.76
    Jan
    0.73
     Jan
    0.73
     JAN
    0.72
     January
    0.71
     JANUARY
    0.69
    January
    0.68
     janu
    0.66
    uary
    0.65
    Activations Density 0.068%

    No Known Activations