© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 233
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals or groups in a social or political context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 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
    /*
    -0.48
     Hang
    -0.43
    Subview
    -0.43
     Glauben
    -0.42
    carpus
    -0.42
    agissait
    -0.42
    Hang
    -0.41
    featureID
    -0.41
     unknownFields
    -0.40
    PAGER
    -0.40
    POSITIVE LOGITS
     kteří
    0.86
     who
    0.81
    躇
    0.78
     którzy
    0.74
     whoſe
    0.73
     Archiproducts
    0.71
     ktorí
    0.69
    quien
    0.67
    guien
    0.65
     Nadie
    0.65
    Activations Density 0.313%

    No Known Activations