© 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. 8514
    Prev
    Next
    INDEX
    Explanations

    technical terms and components related to software development, particularly in identity and authentication systems

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     noDo
    -0.42
    PyExc
    -0.41
    moneda
    -0.40
    snapshots
    -0.40
     sterilized
    -0.39
     Reuter
    -0.39
     Sna
    -0.38
     محفوظة
    -0.37
     currency
    -0.36
    Currency
    -0.35
    POSITIVE LOGITS
     SAM
    0.64
     federation
    0.63
     OAuth
    0.61
     feder
    0.60
    Feder
    0.59
    SAM
    0.59
     SSO
    0.59
     Federation
    0.58
     authentic
    0.57
    idp
    0.57
    Activations Density 0.432%

    No Known Activations