© 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. 4491
    Prev
    Next
    INDEX
    Explanations

    terms related to research methodologies or experimental contexts

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

    Follows articles or symbols

    np_acts-logits-general · gemini-2.0-flash

    political and economic terms

    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
     pretty
    -0.65
     mostly
    -0.59
     probably
    -0.57
     Mostly
    -0.57
    ból
    -0.55
     maybe
    -0.55
     quite
    -0.55
     usually
    -0.54
    Mostly
    -0.54
    mostly
    -0.53
    POSITIVE LOGITS
    NUMX
    0.88
    adaptiveStyles
    0.86
    jsxFileName
    0.80
     esternos
    0.79
    AndEndTag
    0.79
     nation
    0.75
     patriotic
    0.74
     unity
    0.74
    twimg
    0.73
    atguigu
    0.73
    Activations Density 0.240%

    No Known Activations