© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 35-GEMMASCOPE-RES-16K
    11. 5888
    Prev
    Next
    INDEX
    Explanations

    conditional phrases and logical constructs in arguments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Wiktionnaire
    -0.43
     intptr
    -0.40
    ंदीखरीदारी
    -0.36
     quidem
    -0.35
    )$/,
    -0.34
    SuspendLayout
    -0.33
     kaarangay
    -0.32
    itschrift
    -0.32
    новништво
    -0.31
    hoga
    -0.31
    POSITIVE LOGITS
     otherwise
    4.59
     Otherwise
    4.13
    otherwise
    4.03
    Otherwise
    4.03
     OTHERWISE
    3.39
     altrimenti
    3.17
     sonst
    3.02
    否则
    2.91
     иначе
    2.89
    不然
    2.66
    Activations Density 1.102%

    No Known Activations