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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 15067
    Prev
    Next
    INDEX
    Explanations

    instances of the word "ard" or its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     suena
    -0.48
    IntoConstraints
    -0.47
     afloat
    -0.42
    DMETHOD
    -0.42
     createSlice
    -0.42
     pieles
    -0.41
    
    -0.41
     favourably
    -0.41
     дописавши
    -0.41
    DotNetBar
    -0.39
    POSITIVE LOGITS
    ard
    1.70
    ards
    1.70
    ARD
    1.68
     ward
    1.64
     Ward
    1.55
    Ward
    1.55
     WARD
    1.46
    arding
    1.33
    ward
    1.31
    arda
    1.30
    Activations Density 0.331%

    No Known Activations