© 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. 30-GEMMASCOPE-RES-16K
    11. 8678
    Prev
    Next
    INDEX
    Explanations

    concepts related to religious themes of grace, love, and redemption

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Religious concepts of repentance and forgiveness

    np_acts-logits-general · gemini-2.0-flash

    sin and repentance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/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.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kasarigan
    -0.51
     soñar
    -0.50
    tahankan
    -0.49
    Datuak
    -0.48
     Organisator
    -0.47
     desmotivaciones
    -0.46
     mulia
    -0.45
    期刊论文
    -0.45
    vedades
    -0.45
    她們
    -0.45
    POSITIVE LOGITS
     forgiveness
    0.72
     salvation
    0.72
     redemption
    0.66
     repent
    0.63
     sins
    0.62
     pardon
    0.60
     forgiven
    0.60
     atonement
    0.59
     Forgiveness
    0.56
     sinner
    0.56
    Activations Density 0.113%

    No Known Activations