© 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. 477
    Prev
    Next
    INDEX
    Explanations

    references to web links and online sources

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

    Text within quotation marks

    np_acts-logits-general · gemini-2.0-flash

    ‘Why’ and ‘how’ statements

    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
     AssemblyCulture
    -1.03
    ViewFeatures
    -0.77
     thereto
    -0.74
    abestanden
    -0.69
    TagHelper
    -0.68
    :✨
    -0.67
     CHAPITRE
    -0.66
     Roskov
    -0.65
    SPATH
    -0.64
    AnchorStyles
    -0.63
    POSITIVE LOGITS
     ‘
    0.80
     Why
    0.80
     How
    0.75
     '
    0.75
    ‘
    0.72
    Why
    0.71
    How
    0.69
    ANALYSIS
    0.68
     how
    0.68
     “
    0.67
    Activations Density 0.085%

    No Known Activations