© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 14523
    Prev
    Next
    INDEX
    Explanations

    references to XML schemas and versions related to programming or markup languages

    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
    JspWriter
    -0.80
    +:+
    -0.76
    ########.
    -0.67
    gnore
    -0.65
     <=",
    -0.63
     AssemblyProduct
    -0.62
    Хьажоргаш
    -0.59
    +#+#
    -0.59
    RegistryLite
    -0.58
    aVar
    -0.57
    POSITIVE LOGITS
    TagHelpers
    0.84
    vironment
    0.54
    Validation
    0.48
    FormTagHelper
    0.48
     Eins
    0.47
    łaszcza
    0.47
     immig
    0.46
    legged
    0.46
    AnchorTagHelper
    0.46
    Copied
    0.46
    Activations Density 0.078%

    No Known Activations