© 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-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 6975
    Prev
    Next
    INDEX
    Explanations

    Java programming constructs and variable declarations

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

    Abbreviations followed by punctuation

    np_acts-logits-general · gemini-2.0-flash

    variable initializations

    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
     noblest
    -0.59
    fjspx
    -0.55
    RenderAtEndOf
    -0.54
    ticale
    -0.51
    ACTED
    -0.50
    culi
    -0.50
    躇
    -0.50
    ismet
    -0.49
    choly
    -0.49
     contd
    -0.49
    POSITIVE LOGITS
    Autoritní
    0.42
     '\\;'
    0.34
    imageshack
    0.34
    Personensuche
    0.31
    (__('
    0.31
    الحياه
    0.31
     فهي
    0.31
     saites
    0.30
     comuniques
    0.29
     EconPapers
    0.29
    Activations Density 2.544%

    No Known Activations