© 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. 3-GEMMASCOPE-RES-16K
    11. 7353
    Prev
    Next
    INDEX
    Explanations

    verbs related to actions and processes in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -0.75
     Normdatei
    -0.67
     plufieurs
    -0.65
     ſta
    -0.64
     ſtate
    -0.62
    titleMargin
    -0.61
    genodigd
    -0.59
    でもあります
    -0.59
    AccessorTable
    -0.59
     Chwiliwch
    -0.59
    POSITIVE LOGITS
    する
    2.20
    した
    1.56
    して
    1.36
     する
    1.16
    하는
    1.12
    し
    0.98
    すると
    0.95
    します
    0.91
     した
    0.84
     하는
    0.79
    Activations Density 0.020%

    No Known Activations