© 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. 41-GEMMASCOPE-RES-16K
    11. 4059
    Prev
    Next
    INDEX
    Explanations

    relationships and comparisons among various subjects

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     increí
    -1.48
    нгред
    -1.45
     indígen
    -1.45
     Azevedo
    -1.44
     Schmitz
    -1.41
    rungsseite
    -1.41
    ementara
    -1.39
     queſta
    -1.39
     للاسماء
    -1.39
     pérd
    -1.38
    POSITIVE LOGITS
    <bos>
    0.34
    Ta
    0.07
    Mag
    0.01
     Nio
    0.01
    Cab
    0.01
    PDB
    0.00
    Br
    -0.00
    Pi
    -0.00
    Phi
    -0.00
     Pamp
    -0.01
    Activations Density 1.351%

    No Known Activations