© 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. 33-GEMMASCOPE-RES-16K
    11. 13330
    Prev
    Next
    INDEX
    Explanations

    phrases and statements that indicate significant events or mentions of specific groups and their experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -0.41
     Chwiliwch
    -0.36
     '\\;'
    -0.32
    ViewFeatures
    -0.31
    なきゃ
    -0.31
     Reverso
    -0.30
     Особенно
    -0.29
    ganu
    -0.29
     Gotta
    -0.28
    SizeF
    -0.28
    POSITIVE LOGITS
     tidak
    1.89
     nicht
    1.89
     not
    1.88
     não
    1.81
     doesn
    1.78
    ไม่ได้
    1.69
     neither
    1.68
     didn
    1.66
     không
    1.65
     δεν
    1.62
    Activations Density 7.508%

    No Known Activations