© 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. 3-GEMMASCOPE-RES-16K
    11. 6157
    Prev
    Next
    INDEX
    Explanations

    references to the geographic region of South in various contexts

    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
    PMailer
    -0.50
     HasFactory
    -0.45
    úgó
    -0.43
    uride
    -0.40
    tijden
    -0.40
     nisso
    -0.40
     legen
    -0.39
     casó
    -0.39
    klär
    -0.38
    CastException
    -0.38
    POSITIVE LOGITS
     South
    4.16
    South
    3.89
     SOUTH
    3.31
    south
    2.91
     south
    2.86
    SOUTH
    2.70
     North
    2.23
    南
    2.17
    North
    2.05
     Süd
    1.96
    Activations Density 0.062%

    No Known Activations