© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 405
    Prev
    Next
    INDEX
    Explanations

    technical terms and conditions related to voltage and current in electrical systems

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

    Electromagnetic or radio frequency interference

    np_acts-logits-general · gemini-2.0-flash

    electromagnetic interference

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    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
     joindre
    -0.35
    Spéc
    -0.32
     föruts
    -0.31
    chieht
    -0.31
     sĩ
    -0.31
    あんな
    -0.31
     revenir
    -0.30
     prospect
    -0.30
     GenerationType
    -0.30
     montanha
    -0.30
    POSITIVE LOGITS
     AssemblyCompany
    0.58
     kasarigan
    0.57
     contamin
    0.57
     snippetHide
    0.54
     contamination
    0.54
    bootstrapcdn
    0.52
    OCCURRED
    0.51
     initComponents
    0.50
    setVerticalGroup
    0.49
     noise
    0.48
    Activations Density 0.763%

    No Known Activations