© 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. 10-GEMMASCOPE-RES-16K
    11. 4680
    Prev
    Next
    INDEX
    Explanations

    phrases indicating prior notice or preparation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Tras
    -0.36
     склад
    -0.36
     finally
    -0.35
    NgModule
    -0.35
    strSql
    -0.34
     rev
    -0.34
     reciente
    -0.33
    FormState
    -0.33
    Prop
    -0.33
     Slo
    -0.33
    POSITIVE LOGITS
     antemano
    1.03
     vooraf
    0.98
     заранее
    0.97
    提前
    0.95
     beforehand
    0.90
     advance
    0.84
     anticipo
    0.82
     ahead
    0.81
     adelantado
    0.79
     anticip
    0.79
    Activations Density 0.410%

    No Known Activations