© 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. 13535
    Prev
    Next
    INDEX
    Explanations

    discussions around religious themes and personal beliefs

    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
    ñores
    -0.43
     Efq
    -0.39
    PerformLayout
    -0.39
     Monfieur
    -0.35
    dafx
    -0.35
     Geben
    -0.33
    قایناق‌لار
    -0.32
     compensated
    -0.32
    .*")]
    -0.31
     guerr
    -0.31
    POSITIVE LOGITS
     religious
    2.14
     Religious
    1.98
    Religious
    1.90
    religious
    1.88
     religion
    1.88
     Religion
    1.81
    Religion
    1.74
     religios
    1.70
     RELIG
    1.69
     religiosa
    1.64
    Activations Density 1.245%

    No Known Activations