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. 731
    Prev
    Next
    INDEX
    Explanations

    references to the quality of healthcare services and their assessment

    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
    parsedMessage
    -0.74
     nakalista
    -0.71
    ArgsConstructor
    -0.70
    GenerationType
    -0.69
     consultato
    -0.66
    ьаж
    -0.65
    complexContent
    -0.63
    XmlAccessType
    -0.63
    sidemargin
    -0.62
    djangoproject
    -0.62
    POSITIVE LOGITS
     providing
    2.28
     Providing
    2.17
    Providing
    2.17
     provide
    2.10
    providing
    2.09
    provide
    1.99
     provided
    1.97
    Provide
    1.93
     Provide
    1.92
    提供
    1.89
    Activations Density 0.461%

    No Known Activations