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. 996
    Prev
    Next
    INDEX
    Explanations

    code structure elements associated with error handling and exceptions

    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
     Promotion
    -0.70
     promotion
    -0.69
    ChildScrollView
    -0.68
    Билгалдахарш
    -0.64
    UserScript
    -0.64
    promotion
    -0.64
    ANTLR
    -0.62
     Roskov
    -0.61
    Personendaten
    -0.60
     promoción
    -0.59
    POSITIVE LOGITS
    mıştır
    0.49
     kepala
    0.45
     gia
    0.45
     chín
    0.44
     onlyOwner
    0.42
    onomía
    0.42
    例句
    0.41
     compañero
    0.41
    COA
    0.41
    Header
    0.40
    Activations Density 0.205%

    No Known Activations