© 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. 35-GEMMASCOPE-RES-16K
    11. 9217
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate considerations or conditions in discussions or analyses

    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
     and
    -0.37
     EClass
    -0.35
    木坂
    -0.35
    委会
    -0.33
     bin
    -0.33
    
    -0.32
    AnchorTagHelper
    -0.32
     Италијани
    -0.32
    的情况下
    -0.31
    رشف
    -0.31
    POSITIVE LOGITS
     betreft
    0.79
     riguarda
    0.66
     regard
    0.64
     '\\;'
    0.63
     regards
    0.61
    regard
    0.61
     gäller
    0.56
     específicamente
    0.56
     specifically
    0.56
     betrekking
    0.54
    Activations Density 0.217%

    No Known Activations