© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 35-GEMMASCOPE-RES-16K
    6. 8542
    Prev
    Next
    INDEX
    Explanations

    references to church activities and elements of community engagement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ोंने
    -0.33
     htmlFor
    -0.31
     agricoles
    -0.30
     cav
    -0.28
    cleros
    -0.28
     Muhammad
    -0.27
    hotels
    -0.27
     recommandons
    -0.27
     Procu
    -0.26
     nobile
    -0.24
    POSITIVE LOGITS
     congregation
    1.12
     Sunday
    1.11
    Sunday
    1.09
     Sundays
    1.04
     worship
    1.02
     sunday
    0.97
    sunday
    0.96
     congre
    0.96
    SUNDAY
    0.94
     SUNDAY
    0.93
    Activations Density 0.221%

    No Known Activations