© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 16126
    Prev
    Next
    INDEX
    Explanations

    statistical analysis terms and methodologies related to experiment results

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

    academic or scientific study contexts and research methodology terms.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered 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
     nonUne
    -0.69
    Personensuche
    -0.66
     ExecuteAsync
    -0.63
     سكانية
    -0.61
     noDo
    -0.61
    findpost
    -0.61
    +#+#
    -0.61
     AssemblyCompany
    -0.59
    MENAFN
    -0.59
    Tembelea
    -0.57
    POSITIVE LOGITS
     psychologists
    0.60
     psychologist
    0.54
     Psychology
    0.51
     psych
    0.50
     Psychologist
    0.49
     psychological
    0.48
     Psych
    0.44
    心理学
    0.44
     psychology
    0.44
    Psych
    0.43
    Activations Density 0.573%

    No Known Activations