© 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-2-2B
    7. Residual Stream - 16k
    9. 8-GEMMASCOPE-RES-16K
    11. 662
    Prev
    Next
    INDEX
    Explanations

    quantities and expressions referring to a large number of items or occurrences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AfterClass
    -0.89
     FLA
    -0.75
    AdapterView
    -0.69
    </b>
    -0.68
    Beats
    -0.67
     dovrebbero
    -0.65
    Fla
    -0.61
    EventQueue
    -0.61
     totales
    -0.61
     azzurro
    -0.60
    POSITIVE LOGITS
    MANY
    1.66
     MANY
    1.65
     many
    1.57
    many
    1.38
     Many
    1.32
    Many
    1.25
     muchos
    1.14
     Muitos
    1.05
    Viele
    1.03
    Muchos
    1.03
    Activations Density 0.092%

    No Known Activations