© 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. 15-GEMMASCOPE-RES-16K
    11. 1139
    Prev
    Next
    INDEX
    Explanations

    Indented block declarations and code structure in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RegressionTest
    -0.82
    MessageOf
    -0.82
     intptr
    -0.79
    RenderAtEndOf
    -0.77
     nahilalakip
    -0.77
     disambiguazione
    -0.76
    AddTagHelper
    -0.74
     kasarigan
    -0.74
    曖昧さ回避
    -0.74
     ModelExpression
    -0.73
    POSITIVE LOGITS
     saati
    0.46
     península
    0.41
     Usaha
    0.37
     Partai
    0.34
     bahía
    0.34
     equipes
    0.34
     civilización
    0.32
     ruedas
    0.32
     Profitez
    0.32
     Ayuntamiento
    0.32
    Activations Density 0.190%

    No Known Activations