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. 12-GEMMASCOPE-RES-16K
    6. 9497
    Prev
    Next
    INDEX
    Explanations

    mentions of institutions, titles, and individuals associated with academic or research contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     generalized
    -0.60
    PerformLayout
    -0.60
     generalised
    -0.58
     Vendors
    -0.57
     supervisor
    -0.54
    sendStatus
    -0.54
     <<<<<<<<<<<<<<
    -0.53
    ROUTE
    -0.53
     múl
    -0.52
     Jurí
    -0.52
    POSITIVE LOGITS
    发表于
    0.64
    InvalidProtocol
    0.63
    Хьажоргаш
    0.62
     philanthrop
    0.62
     betweenstory
    0.61
    niosek
    0.60
     Foundation
    0.59
    DataSnapshot
    0.58
    EnableWeb
    0.58
     CWE
    0.56
    Activations Density 0.357%

    No Known Activations