© 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. 8346
    Prev
    Next
    INDEX
    Explanations

    syntactical or formatting elements in data

    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
    
    -0.89
     kaarangay
    -0.79
     PeEnEo
    -0.69
     InputDecoration
    -0.68
     Autorisations
    -0.68
    NameInMap
    -0.67
     مشين
    -0.66
    GEBURTSDATUM
    -0.65
    principalColumn
    -0.65
     الرياضيه
    -0.62
    POSITIVE LOGITS
    ][
    0.82
    )(
    0.59
    <u>
    0.35
     poem
    0.35
     review
    0.34
    式の
    0.34
     lecz
    0.33
     Harness
    0.33
    Harness
    0.32
     pairs
    0.32
    Activations Density 0.031%

    No Known Activations