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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 14927
    Prev
    Next
    INDEX
    Explanations

    specific titles or quotes of books and publications

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

    Text within quotation marks, often titles

    np_acts-logits-general · gemini-2.0-flash

    introduces titles

    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
     تضيفلها
    -0.70
    出版年
    -0.53
     typelib
    -0.51
     فريبيس
    -0.51
     cuillère
    -0.51
     rowspan
    -0.50
    phinx
    -0.50
     Gossip
    -0.50
     REFER
    -0.50
     GBIF
    -0.50
    POSITIVE LOGITS
     The
    0.68
     titulada
    0.60
     entitled
    0.56
    SequentialGroup
    0.56
    cektir
    0.56
    unate
    0.54
    見えて
    0.53
    ISupport
    0.53
    ままで
    0.52
     berjudul
    0.52
    Activations Density 0.124%

    No Known Activations