© 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-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 8742
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize comparison or contrast using the word "as"

    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
    CppMethod
    -0.82
     myſelf
    -0.81
     itſelf
    -0.71
     faggot
    -0.70
    WillAppear
    -0.69
    writeFieldEnd
    -0.67
    MessageOf
    -0.66
    Enllaços
    -0.65
     himſelf
    -0.64
    </caption>
    -0.64
    POSITIVE LOGITS
    onAttach
    0.56
    estacks
    0.55
    feira
    0.54
     what
    0.54
     As
    0.52
    MouseClicked
    0.51
     Ancak
    0.49
    +:+
    0.49
    usermodel
    0.48
    saraba
    0.48
    Activations Density 0.257%

    No Known Activations