© 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. 3-GEMMASCOPE-RES-16K
    11. 8694
    Prev
    Next
    INDEX
    Explanations

    verbs used in various grammatical forms to describe existence, capability, or relation

    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
     autorytatywna
    -0.98
    ſſung
    -0.93
     erſt
    -0.91
     ſehen
    -0.90
    <unused52>
    -0.89
    <unused53>
    -0.89
    <unused68>
    -0.89
     ſehr
    -0.88
    <unused55>
    -0.88
    <unused14>
    -0.88
    POSITIVE LOGITS
     is
    0.75
     has
    0.59
     was
    0.45
     will
    0.45
    ’
    0.44
     are
    0.41
     may
    0.41
    是
    0.39
     doesn
    0.36
     welches
    0.36
    Activations Density 0.513%

    No Known Activations