© 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. 3403
    Prev
    Next
    INDEX
    Explanations

    measurements and percentages related to chemical processes or materials

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

    paper or slurry

    np_acts-logits-general · gemini-2.0-flash

    toilet paper and coloured paper

    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
    ConstraintMaker
    -0.61
    +#+#
    -0.55
     snippetHide
    -0.51
    tinyos
    -0.49
     sò
    -0.49
    quelize
    -0.49
    脚注の使い方
    -0.48
     vacun
    -0.45
    Weblinks
    -0.45
     Eis
    -0.45
    POSITIVE LOGITS
     paper
    1.77
     Paper
    1.60
    paper
    1.58
    Paper
    1.54
     PAPER
    1.45
    PAPER
    1.39
     papers
    1.29
     Papers
    1.21
    papers
    1.18
     Papier
    1.14
    Activations Density 0.229%

    No Known Activations