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. 16-GEMMASCOPE-RES-16K
    6. 1613
    Prev
    Next
    INDEX
    Explanations

    specific technical specifications and compatible features of electronic devices

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

    Comes before coordinating conjunctions or conjunctive adverbs

    np_acts-logits-general · gemini-2.0-flash

    experiences and facilities

    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
    出版年
    -0.67
    🏻‍♀️
    -0.57
    Obrigada
    -0.57
    Приятного
    -0.57
    qrstuvwxyz
    -0.56
     sessionFactory
    -0.56
    Hashtag
    -0.55
     دیکھیے
    -0.55
     codon
    -0.55
     cds
    -0.55
    POSITIVE LOGITS
     nicely
    0.62
     surprisingly
    0.58
    RenderAtEndOf
    0.57
     unsur
    0.57
     impressively
    0.57
     admirably
    0.56
     MSRP
    0.55
    [+]
    0.55
     outright
    0.55
     oddly
    0.54
    Activations Density 0.303%

    No Known Activations