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. 21-GEMMASCOPE-RES-16K
    6. 407
    Prev
    Next
    INDEX
    Explanations

    statements regarding mathematical definitions, properties, and relationships

    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
     audacity
    -0.57
    DOCTYPE
    -0.51
     спе
    -0.50
    dopodob
    -0.49
    かげ
    -0.48
    threatening
    -0.47
     Readiness
    -0.47
    popper
    -0.45
    prof
    -0.44
    letti
    -0.44
    POSITIVE LOGITS
    UnusedPrivate
    0.87
     صوتيه
    0.78
    Архівовано
    0.70
    EDEFAULT
    0.68
    CloseOperation
    0.64
    lloworld
    0.64
    脚注の使い方
    0.62
     OFDb
    0.62
    ainville
    0.62
    存于互联网档案馆
    0.62
    Activations Density 1.551%

    No Known Activations