© 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. 3-GEMMASCOPE-RES-16K
    11. 8742
    Prev
    Next
    INDEX
    Explanations

    references to specific villas or notable properties

    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
    ToProps
    -0.54
    apan
    -0.51
    opardi
    -0.50
     noqa
    -0.50
    unnitel
    -0.49
     onBackPressed
    -0.49
    apte
    -0.49
    HeaderComponent
    -0.48
     wandering
    -0.48
    odacty
    -0.48
    POSITIVE LOGITS
     Sil
    0.83
     Gil
    0.82
    Sil
    0.81
    Gil
    0.79
     SIL
    0.78
     Silas
    0.76
     Silk
    0.73
     Gill
    0.72
    Kil
    0.71
     sil
    0.71
    Activations Density 0.167%

    No Known Activations