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. 15-GEMMASCOPE-RES-16K
    6. 2387
    Prev
    Next
    INDEX
    Explanations

    instances of the word "having" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fikasi
    -0.78
    rsiniz
    -0.63
     المنام
    -0.63
     Vikipedi
    -0.61
    kå
    -0.61
     Crypt
    -0.61
     zircon
    -0.60
     BSEB
    -0.60
     Folge
    -0.59
     Ruh
    -0.58
    POSITIVE LOGITS
    RenderAtEndOf
    0.79
    ting
    0.76
     taking
    0.71
    ly
    0.71
    ating
    0.70
    Билгалдахарш
    0.69
    gggg
    0.68
    ying
    0.67
    izing
    0.66
    ging
    0.66
    Activations Density 0.490%

    No Known Activations