© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 40-GEMMASCOPE-RES-16K
    11. 8763
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to flattery or excessive praise

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    omitempty
    -0.39
    จำ
    -0.35
     escur
    -0.33
    цездатний
    -0.33
     Avez
    -0.33
     للاسماء
    -0.32
    Captor
    -0.32
     ويكيميديا
    -0.32
     ampliamente
    -0.32
     Desarrollo
    -0.31
    POSITIVE LOGITS
    cked
    0.65
    pping
    0.63
    ck
    0.63
    kes
    0.62
    cking
    0.60
    CK
    0.59
    ckle
    0.58
    gging
    0.58
    cks
    0.57
    pped
    0.57
    Activations Density 0.621%

    No Known Activations