© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 16333
    Prev
    Next
    INDEX
    Explanations

    code-related terms and constructs involving programming modules and components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     siy
    -0.32
     do
    -0.31
    ikon
    -0.31
     хватает
    -0.31
     RESID
    -0.30
     ikan
    -0.30
     still
    -0.30
     reunir
    -0.29
     réalise
    -0.29
    ia
    -0.29
    POSITIVE LOGITS
     kasarigan
    0.96
    TagMode
    0.90
    KURZBESCHREIBUNG
    0.88
    rungsseite
    0.77
     BoxFit
    0.77
     AssemblyProduct
    0.75
    ImageContext
    0.74
     contextLoads
    0.73
     autorytatywna
    0.73
    VersionUID
    0.72
    Activations Density 0.254%

    No Known Activations