© 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-2-9B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 16237
    Prev
    Next
    INDEX
    Explanations

    key terms related to procedures and conditions in scientific or technical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     snippetHide
    -0.57
     jScrollPane
    -0.46
    ReusableCell
    -0.45
    CloseOperation
    -0.45
     Paglinawan
    -0.44
    addContainerGap
    -0.44
     metodología
    -0.43
     defStyle
    -0.43
     consultato
    -0.43
     مشين
    -0.42
    POSITIVE LOGITS
    Abitanti
    0.56
    hili
    0.50
    Tikang
    0.49
    utives
    0.49
    ety
    0.45
     Mirror
    0.45
    uwa
    0.45
    uted
    0.43
    __]
    0.43
     Tully
    0.43
    Activations Density 1.137%

    No Known Activations