© 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-2-9B
    7. Residual Stream - 16k
    9. 38-GEMMASCOPE-RES-16K
    11. 15891
    Prev
    Next
    INDEX
    Explanations

    information about personal integrity and honesty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    majánló
    -0.90
     verſch
    -0.87
     Geiſt
    -0.84
     fashiola
    -0.82
     beſch
    -0.82
     dieſen
    -0.82
     ſeines
    -0.81
     فريبيس
    -0.81
     fieltro
    -0.81
    ðsíða
    -0.80
    POSITIVE LOGITS
     AND
    0.66
     IT
    0.56
     OF
    0.52
     IS
    0.51
     R
    0.50
     UN
    0.50
     Y
    0.48
     L
    0.48
     SO
    0.47
     WHO
    0.47
    Activations Density 1.276%

    No Known Activations