© 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. 9-GEMMASCOPE-RES-16K
    11. 11190
    Prev
    Next
    INDEX
    Explanations

    locations and contexts specified by the word "where."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     DPS
    -0.47
     Adu
    -0.45
    Puff
    -0.44
    DPS
    -0.43
    onOptions
    -0.43
     Ekiti
    -0.43
    onomian
    -0.43
     Riti
    -0.43
    Offensive
    -0.42
     Yi
    -0.42
    POSITIVE LOGITS
     where
    1.75
    where
    1.64
    Where
    1.45
     Where
    1.42
     WHERE
    1.41
    WHERE
    1.37
     donde
    1.26
     où
    1.16
     dónde
    1.15
    Dónde
    1.13
    Activations Density 0.148%

    No Known Activations