© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 2052
    Prev
    Next
    INDEX
    Explanations

    discussions on forgiveness and repentance in a religious context

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

    forgiveness and repentance

    np_acts-logits-general · gemini-2.0-flash

    concepts of sin and forgiveness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    utilities
    -0.47
     Cliquez
    -0.39
    droje
    -0.39
    Inspir
    -0.39
    __':
    -0.37
    illip
    -0.37
     Chennai
    -0.35
    chaise
    -0.35
     Allegro
    -0.35
    force
    -0.35
    POSITIVE LOGITS
     forgiveness
    0.69
     sins
    0.60
     forgiven
    0.59
     forgive
    0.58
     perdón
    0.57
     Forgiveness
    0.56
    enderror
    0.55
     betweenstory
    0.55
     perdon
    0.52
     guilt
    0.52
    Activations Density 0.228%

    No Known Activations