© 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-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 3551
    Prev
    Next
    INDEX
    Explanations

    HTML form elements and attributes

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

    HTML form-related attributes and tags

    np_acts-logits-general · gemini-2.0-flash

    HTML form submissions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
    verwijspagina
    -0.67
     StatelessWidget
    -0.62
     متعلقه
    -0.58
    MessageTagHelper
    -0.57
    
    -0.55
     colorés
    -0.53
    xase
    -0.53
    ArgsConstructor
    -0.52
     UILabel
    -0.52
    TagMode
    -0.51
    POSITIVE LOGITS
     submit
    1.12
    Submit
    1.05
    submit
    1.03
     Submit
    1.00
     onSubmit
    1.00
     form
    0.99
     submitting
    0.98
     submission
    0.97
     submitted
    0.97
    submitted
    0.93
    Activations Density 0.152%

    No Known Activations