© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 1888
    Prev
    Next
    INDEX
    Explanations

    components related to user interface elements in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    HTML/XML input and form-related elements and attributes.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OGND
    -0.71
    AddTagHelper
    -0.66
    tagHelperRunner
    -0.62
    +#+#
    -0.60
    UnknownFieldSet
    -0.58
     مرئيه
    -0.58
    WaitGroup
    -0.57
     leksikon
    -0.52
    CardBody
    -0.52
    mybatisplus
    -0.51
    POSITIVE LOGITS
    InputTagHelper
    0.57
     TextFormField
    0.39
    TextWatcher
    0.38
    PerformLayout
    0.37
     شماره
    0.35
    TextFormField
    0.35
    input
    0.34
     input
    0.34
    textInput
    0.33
     TextInput
    0.32
    Activations Density 0.107%

    No Known Activations