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

    Neuronpedia

    Jacobian LensNEW
    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. 12768
    Prev
    Next
    INDEX
    Explanations

    specific scientific and technical terms related to biology and research methodologies

    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
     незавершена
    -0.52
     caméra
    -0.52
     Normdatei
    -0.48
    Hozzáférés
    -0.47
     Taktlose
    -0.46
    varlak
    -0.46
    сылкі
    -0.46
     estekak
    -0.46
     ſein
    -0.45
    GTCX
    -0.45
    POSITIVE LOGITS
    tagHelperRunner
    0.49
     actionPerformed
    0.46
     Rind
    0.43
     sna
    0.43
    IActionResult
    0.40
    ReusableCell
    0.40
    tem
    0.38
    ICA
    0.37
     lis
    0.37
     pleasure
    0.36
    Activations Density 2.373%

    No Known Activations