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. 16-GEMMASCOPE-RES-16K
    6. 12357
    Prev
    Next
    INDEX
    Explanations

    references to political and social controversies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    followed by quantities or time periods

    np_acts-logits-general · gemini-2.0-flash

    many years of experience

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/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.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     NUKAT
    -0.69
    djangoproject
    -0.65
    有点
    -0.62
     kics
    -0.61
    simpleType
    -0.60
    หน่อย
    -0.59
    ungkin
    -0.59
     للاسماء
    -0.58
     biraz
    -0.58
     trochu
    -0.57
    POSITIVE LOGITS
     przecież
    0.84
     hundreds
    0.79
     centaines
    0.77
     clearly
    0.76
    hundreds
    0.75
     dozens
    0.73
     countless
    0.73
     thousands
    0.72
    thousands
    0.72
     Hundreds
    0.70
    Activations Density 0.815%

    No Known Activations